On the road to Affine Scattering Transform
|
|
- Marilyn Anthony
- 6 years ago
- Views:
Transcription
1 1 On the road to Affine Scattering Transform Edouard Oyallon with Stéphane Mallat following the work of Laurent Sifre, Joan Bruna,
2 High Dimensional classification (x i,y i ) 2 R 5122 {1,...,100},i= ! ŷ(x)? 22 Training set to predict labels Rhino Caltech 101, etc Rhino class from Caltech 101 Not a rhino
3 3 Translation x y kx yk 2 =2 Rotation Averaging is the key to get invariants x y High dimensionality issues
4 Fighting the curse of dimensionality 4 Geometric variability Groups acting on images: translation, rotation, scaling Class variability Intraclass variability Not informative Other sources : luminosity, occlusion, small deformations x (u) =x(u (u)), 2C 1 I Extraclass variability Can be carefully handled Needs to be learned x x L reduces class variability L x Classifier
5 5 Existing approach Ref.: Discovering objects and their location in images. Sivic et al. High-dimensional Signature Compression for Large-Scale Image Classification, Perronnin et al. Unsupervised learning: Bag of Words, Fisher Vector, {x 1,...,x N }! Supervised learning: Deep Learning, {(x 1,y 1 ),...,(x N,y N )}!L Non learned: HMax, Scattering Transform. {G 1,...}! Ref.: Robust Object Recognition with Cortex-Like Mechanisms. Serre et al.
6 DeepNet? 6 It is a cascade based on a lot of linear operators followed by non linearities. Each operator is supervisedly learned Ref.: Rich feature hierarchies for accurate object detection and semantic segmentation. Girshick et al. Convolutional network and applications in vision. Y. LeCun et al. Sort of Super SIFT State-of-the arts on ImageNet and most of the benchmarks. % accuracy SIFT+FV DeepNet human Ref.: image-net.org
7 Complexity of the architecture 7 Requires a huge amount of data Need many engineering to select the hyper parameters and to optimise it Interpreting the learned operators is hard when the network is deep(i.e. more than 3 layers) Few theoretical results, yet outstanding numerical results. Ref.: Intriguing properties of neural networks, C. Szegedy et al.
8 Operators of a Deep architecture 8 Linear operators are often convolutional whose kernels are small filters. x j (u, 2) =f( X 1 x j 1 (., 1)?h j, 1 (u))! x j = f(f j x j 1 ) Deep. Contains a phase information f is often a ReLu: x! max(0,x) Sometimes pooling which leads to a down sampling.
9 9 Classifier f(f 1 ) f(f 2 ) f(f J ) x 0 x 1 x 2 x J DeepNetwork Ref.: ImageNet Classification with Deep Convolutional Neural Networks. A Krizhevsky et al.
10 Does everything need to be learned? A Scattering Network is a deep architecture, 10 where all the filters are predefined. Ref.: Invariant Convolutional Scattering Network, J. Bruna et Mallat S We challenge the necessity to learn the weights of every filters of a deep architecture. Scattering gets state-of-the-art results on unsupervised learning for some complex datasets. Ref.: Deep Rototranslation Scattering Network for complex Image Recognition, EO, S Mallat We highlight the similarity of the Scattering Network with the DeepNet architectures.
11 <latexit sha1_base64="newmldbod1kkandkku6+pt7tzd8=">aaace3icbzbns0jbfibpts+zr1st2wxkochyb4tqe0gtammqkxhf5o6jds6de5mzg4r4i9q07l+0avhrtk27/k3jr1dacwmp7zmhoef1i86udpwvk7g0vlk6llxpbwxube/yu3u3kowlorus8ldwfkwoz4jwnnoc1ijjcebzwvv7f+n69y5kxujxowcrbqs4i1ibeayn1btzxjuumhpul/xqx2mcxraqv+6ybkfyz51nqj9r2hmn6eyefsgdqaau9vkpafbu2p9ekyrxqiumhctvd51in4zyaky4haw8wneikx7u0lpbgqoqgspjusn0ajwwmjuzjzsaul8nhjhqahd4pjpauqvma2pzv1o91u3txpcjknzukolh7zgjhajxqqjfjcwadwxgipnzfzeulphok2pkhodon7wilapicdg5djolc5gqcqeqhiy4cailuiiyvidaptzbc7xad9az9wa9t1st1mxmh/7i+vggeckd9g==</latexit> sha1_base64="srdvla/owkcv7kmocnqmjpznjn0=">aaace3icbzdlssnafiynxmu9rv26gvqelpasufa3qtcflisyw2hcmuyn7ddjjmxmpkh0iqtxvdy4uhhrxl3fxulf0nyfbj7+cw5zzh/ejeplwsnjaxlldw09s5hd3nre2tx39u9klahmxbyxsnqdjamjnlikkkbqssaodbipbb3lcb12t4skeb9vauz8ehu4bvomllaazslrrwixbvvlh+p4lmormvsqxvrovprf8wn1i00zb1wsieai2dpiozmv9dhy0mrt/pjaeu5cwhvmsmqgbcxkhychkgzkmpusswkee6hdgho5con0b5ojhvbioy2od9kpkzhxf08muchlgga6m0sqk+dry/o/winr7tn/qhmckmlx9kn2wqck4dgh2kkcymvsdqglqnefuisewkrnmnuh2pmnl4j7xdmpwdd23rkau2xaicibardbkxdanagcf2dwaj7bk3gznowx4934mlyugboza/bhxuc3gaaffa==</latexit> <latexit sha1_base64="zbot7jba2tu1iy/+rhd2jwirzvo=">aaacfhicbva9bxnbej0zstamhwzkmlwsslaswhcpgabjgoyihspfiswfsfbwe/bke7un3tnw6eq/quplz6chiiiwgi7/juupirhzpjge3pvrzlwolcki7996psdb2ztpy88qz3f39g+ql15ewz0zxjtms226ebvccsu7kfdybmo4tsljr6pjx7l//yubk7s6xdzl/ysoligfo+ikqfukfx+2x6i+bzdwxkur5deamrojnuz/jdof+7k4dwb1vdgo1vymvwdzjmgk1fqh4fepaggpqv/dowzzwhuysa3tbx6k/yiafezywsxmle8pm9ar7zmqamjtv1h8nsnhthmswbtxcslcvt9r0mtapilcz0jxbne9ufiy18swftcvheoz5iotf8wzjkjjpciyfiyzllkjlbnhbivsta1l6iksubcc9zc3sees+abpxws11gdyogyv4rdqembbamenaemhghydn/abbrzv3i/vj/d32vryvjov4ag8f3ebxz+f</latexit> sha1_base64="yaq/o5/iled4o5cpingjcktvrwy=">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</latexit> <latexit sha1_base64="mmw7b12yit5ppp6c5e2nqa1b1iu=">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</latexit> <latexit sha1_base64="1xfmdujgtthl4upbizcwn8io4km=">aaaccnicbvdlssnafl3xwesr6tln0ck0kcvxos6lblxwmlbqhdczttuhk0mymqgldo/gf/al3lhqcesxupnvnd4w2nrgwugce7n3nijltgnh+bawlldw19ylg8xnre2dxxtv/04lmstuiwlpzcvcinimqkez5rsvsorjinnmnlga+817khvlxk0epjsicu+wlinygym0s343kzhzxe6qr1gvxhw/0wevvsiqveqbww3tslnzjkclxj2rcr3khz8bqco0v/xoqrkyck04vqrtoqkociw1i5yoin6mairjapdo21cby6qcfpllcb0zpypmuaaerhp190soy6wgcwq6y6z7at4bi/957ux3l4kcitttvjdpom7gku7qobjuyziszyegyc sha1_base64="hbbaurjdhcixnua1kcmznk8/ebi=">aaaccnicbvdlssnafj3uv62vqes3q4vqoptehbomunfzwdhce8jkommhtizhzike0l0bd36hgxcqbv0cd/0bp4+fth64cdjnxu69j0wzlcqyxkzpzxvtfao8wdna3tndm/cp7mwscuxcnlbedeikcaocuioqrjqpicgogwmhw+uj334gqtke36k8jx6m+pxgfcolpccseleiegoqnkjp0n6m6l5rqoudgdya0noghzg1q2lnazejpsc1p+qdpi+dvbwy314vwvlmumimsdm1rvt5brkkykzgfs+tjev4ipqkqylhmzf+mf1lbi+10op6kf1cwan6e6jaszr5horogkmbxpqm4n9en1prpv9qnmakcdxbfgumqgrogoe9kghwlnceyu <latexit sha1_base64="gm84j/6ma8kbnher0bkewwdughc=">aaab7xicbza9swnbeibn4lemx1e7braje sha1_base64="ig/w51dvf9qc2vz4ewqmcwtiwzk=">aaab7xicbzc7sgnbfibpxlumt6idnoole x<latexit sha1_base64="ho sha1_base64="ft DATA 11 Desirable properties of a representation Invariance to group G of transformation 8x, 8g 2 G, (g.x) = (x) Stability to noise 8x, y, k (x) (y)k 2 applekx yk 2 <latexit sha1_base64="5afmzqtj9eto92b9zxcfxndiztg=">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</latexit> sha1_base64="6gqom5yxwlht4qvbk4xrawsglro=">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</latexit> Reconstruction properties y = (x) () x = 1 (y) (x) Linear separation of the different classes 8i 6= j, ke( (X i )) E( (X j ))k 2 1 8i, ( (X i )) 1
12 perfectly understood. DATA Success story Scattering for Textures&Digits Non-learned representation have been successively used on: Digits (patterns): Ref.: Invariant Convolutional Scattering Network, J. Bruna and S Mallat 12 Textures (stationary process): Ref.: Rotation, Scaling and Deformation Invariant Scattering for texture discrimination, Sifre L and Mallat S. Small deformations Rotation+Scale +Translation However all the variabilities(groups) here are
13 <latexit sha1_base64="mrzq5xavndn46w+jqs8gobqt3zu=">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</latexit> sha1_base64="hbb0ca2ujpjcwtzdix9084r07wg=">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</latexit> <latexit sha1_base64="vzm3p0o sha1_base64="mkresqa <latexit sha1_base64="mduu63bohmqgld23v sha1_base64="koiyl79c8jdw2tvoq DATA Wavelets 13 Wavelets help to describe signal structures. wavelet iff 2 L 2 (R 2, C) and R R 2 (u)du =0 Learned in the first layers of a DeepNet. is a Wavelets can be dilated in order to be a multi-scale representation of signals, rotated to describe rotations. j, = 1 2 2j (r (u) 2 j ) <latexit sha1_base64="4ywyx8g1ftsjdjseziepbvzr7ik=">aaacjxicbvdlssnafj34rpvvdekmwiqwpcrf1e2h6mzlbwsltq2t6asddvjg5kyoiv/jxl9x46kk4mpfcdjkoa0hbg7nnmude5yqmwmg8awtrk6tb2wwtorbo7t7+6wdwwczrilqngl4iloolpqzn7abaafdufdsozx2nmln6neeqjas8o9hgtk+h4c+cxnbocs71lbcyex4fgbbiajogpyrminnjk4/xvvxkqr+jrofnyuqutw1x0nvlpwnmjghvkzmnjrrjpzdmlmdgeqe9yfwlgxpnelox1gai5wmrsusnmrkgoe0p6ippsr78fzmrd9vykb3a6ged/pc/t0ry0/kqeeopidhjbe9vpzp60xgxvvj5ocruj9ki9yi6xdoawf6galkge8vwuqw9vedjlcqbfszrvwcuxjymmnxaxc14+683lzo2yigy3sckshel6ij Design wavelets selective to an informative Ref.: ImageNet Classification with Deep Convolutional Neural Networks. j, <latexit sha1_base64="h0os0qpccwgody3iax5x9vow0te="> A Krizhevsky et al. Isotropic variability. ˆ VS ˆ Non-Isotropic
14 14 (u) = 1 2 e kuk 2 2 (e i.u apple) (u) = 1 2 e kuk 2 2 (for sake of simplicity, formula are given in the isotropic case) The Gabor wavelet
15 15 Wavelet Transform Wavelet transform : Wx = {x? j,,x? J },japplej! 2 Isometric and linear operator, with kwxk 2 X Z Z = x? j, 2 +,japplej Covariant with translation x? 2 J! 1 W (x =c )=(Wx) =c Nearly commutes with the action of diffeomorphism k[w,. ]kappleckr k Ref.: Group Invariant Scattering, Mallat S Why wavelets are not enough? Invariance
16 Filter bank implementation 16 of a Fast WT Ref.: Fast WT, Mallat S, 89 Assume it is possible to find h and g such that Set: ˆ (!) = 1 p 2 ĝ (! 2 ) ˆ(! 2 ) and ˆ(!) = 1 p2 ĥ(! 2 ) ˆ(! 2 ) x j (u, 0) = x? j (u) =h?(x? j 1 )(2u) and x j (u, ) =x? j, (u) =g? (x? j 1 )(2u) The WT is then given by Wx = {x j (., ),x J (., 0)} japplej, A WT can be interpreted as a deep cascade of linear operator, which is approximatively verified for the Gabor Wavelets.
17 ˆj = 1 p 2 ĥ(. 2 ) ˆj 1 ˆj, = 1 p 2 ĝ (. 2 ) ˆj 1 DATA 17 g h g h g h x 0 x 1 x 2 x 3 There is an oversampling h 0 Deep implementation of a WT
18 <latexit sha1_base64="uml5obii+vze+lgikfghfeb1kh4=">aaacdxicbva9swnbej3z2/gvtdnmmqoweu4svaqhycnweywrcuhy20zm6t6hu3ncofja2fhxbcxubo3t/dduegu/hiy8ew+g2xlhqqqh1/1wrkbhxicmp6ylm7nz8wvfxauzk2raye0kkthniteoziw1kqtwpnxio1bhpbw67pv1g9rgjvepdvnsrvwilm0pofkpkg74yja3ecap/pwykfs+dzbs6fe2mk19hdfsociw3li7aptlvc9sqqzcronfnsi++61ezbhgjbq3pug5ktvzrkkkhb2cnxlmubjif9iwnoyrmmy+ok sha1_base64="kbet0gcnjjehonqwcqcfkvxlyrc=">aaab43icbvbns8naej34wenx9eplsqiesujbpqpepfywttcgstls2qwb3ba7euroh/dgrfhqf/lmv3h7awrrg4hhezpmzeskkswgwze3tr6xubvd2/f39/z9g8p60apvpwe8ylpq00mo5viohqfaytuf4trpjg8no9up337ixgqthnbc8dinayuywsg6qdwvn4jmmanzjegcngcbfv2zl2pw5lwhk9tabhgugffuogcst/xeaxlb2ygoendrrxnu42p25oscosulmtaufjkz+nuiorm14zxxntnfov32puj/xrfe7dquhc sha1_base64="gwxpyxqnm5vzokdkiviilii+kji=">aaacdxicbva9swnbej2lxzf+rs1tfivgeclfqm0ewuasfiwkuxds7c2znxsf7s4j4cgvspgv2fio2nrb+w/cxicfdxbevdfd7lwgu9kq6747pynjqemz8mxlbn5hcam6vhjm0lwlbilupfoi4aavtlbfkhrezbp5hcg8d3ohq//8brwraxjk/qw7mb9mzcqfjyv51zqnbhpifbnnfve+rhvurbkln6gzw3skr9mrx91wg+4i7c9pjskgjhhsv9+8mbv5jakjxy1pn92mogxxjixcqcxldwzc9pglti1neiymu4zogbcavu sha1_base64="jgrkmmn/j+mnpd5nimdb/px4pni=">aaacdxicbvc7sgnbfj31gemramkzgaiwiwwsvaqhycnwevwtyc7l7oqmgtp7coauejz8gy2/ymohymtv5984ersaegdg3hpu5c49qskfrtv+thywl5zxvnnr+fwnza3tws7ury5txchhsyxvm2aapijaqyesmokcfgysgkh/yuq3hkbpeuc3oejac1k3eh3bgrrjl5rcazrbzbfnbnbni7klpubtusmynbur4z5e+ywixbhhopokoivfmkxdl3y57ziniutijdo6vbut9dkmuhajw7ybakgy77mutaynwajay8bndgnjkg sha1_base64="bsw+/z7xfttmfprw/becc1nu/m8=">aaacdxicbvc7sgnbfj31genr1djmmaqsqti1ubgegi1yrtamka3l7oqmgtp7coauejz8gy2/ymohymtv5984ersaegdg3hpu5c49qskfrsf5thywl5zxvnnr+fwnza1te2f3vsep4ldjsyxvi2aapiighgilnbiflawk1ip+xcivp4dsio5ucjbak2tdshqez2gk3y560js3ms/ovezofyupe4cm9iylamppwj298u2cu3bgoppenzicmalq219eo+zpcbfyybruuk6crywpffzcmo+lghlg+6wltumjfojuzenzhrrold sha1_base64="xzvxeir+93c6votukygk/emnraa=">aaacdxicbvc7sgnbfj31bxxf7bqzxaqlcbswkoiqsbfbigcmkf2w2cmngz19ohnxceuwsrlxv2wsvnla2/kj1k4eha8da+eecy937gltktq6zoc1mjo2pje5nv2ymz2bxygulp3pjfmcqjyritopmqypyqiiqannqqiwhrjq4dvbz6/dgniiiu+xnyifsytynavnaksguo5j09xggdj38stabhryajsl19mkpvykxnojogg7jacp+pe4q2kxv+7sz9vjbiuovnunhgcrxmgl07ruoin6ovmouirowcs0pixfsquogxqzcl DATA 18 Scattering Transform Scattering transform at scale J is the cascading of complex WT with modulus non-linearity, followed by a low pass-filtering: S J x = {x? J, x?? 1 J, with x? 1? 2? J } Ref.: Group Invariant Scattering, Mallat S i = {j i, i },j i apple J Depth J x J. J. Mathematically well defined for a large class of wavelets.
19 19 For people into computer vision: SIFT performs a histogram of gradient h( ) = X kgk Gradient \g2[, + ] = X g k1 \g2[, + ] gk Quantification x?? The averaging leads to a loss of information Relations with SIFT
20 x<latexit sha1_base64="vbwja9ly6q sha1_base64="a9ccdmxj8b <latexit sha1_base64="ukn0lywidnxbhx5lbgpech2pnps=">aaab/3icbzdlssnafizpvnz6i7pw4wzoeqshjc7uzdgnywrgfppqjtnjo3qyctmtsatd+cscgxcqbn0nd76n04ugrt8mfpznhm6cp0w5u9pxvqyfxaxlldxcwnf9y3nr297zvvvjjgn1smit2qixopwj6mmmow2kkui45lqe9i5h9fodlyol4kb3uxreucnyxajwxmr sha1_base64="dabp+plfweonh5yldjzxj4ckpke=">aaab/3icbzdlssnafiyn9vbrlerchzuhrrcekrhql0e3lisyw2hcmuwn7ddjhzktmbtd+ay+grsxkm59dxd9g6cxqvt/gpj4zzmcox+qcq7askzgywl5zxwtuf7a2nza3jf39+5ukknkxjqirdycopjgmxobg2cnvdisbylvg97vuf6/z1lxjl6fpgv+rdoxdzklok2 DATA Feature map 20 x? <latexit sha1_base64="op27vgr2x2ta/4mkmq73cw5enzi=">aaab8xicbzc7sgnbfibpxlumt6ilfonbsaq7fmoztlfmwdxc7hjmj7pjknklm2ffsoqxbcxubh sha1_base64="b6t5l4p5wmchnzolv7uguqh4nks=">aaab8xicbzdlssnafiyn9vbrrepskceiucqjc3vzdooybwmlssit6aqdopmemroxhc59bdcuvn x?? 1st order coefficients Example of Scattering coefficients
21 21 Properties Non-linear Ref.: Group Invariant Scattering, Mallat S Isometric ks J xk = kxk Stable to noise ks J x S J ykapplekx yk Covariant with translation S J (x =c )=S J (x) =c Invariant to small translation c apple2 J ) S J (x =c ) S J (x) Sensitive to the action of rotation S J (r x) 6= S J (x) Linearize the action of small deformation ks J x S J xkappleckr k Reconstruction properties Ref.: Reconstruction of images scattering coefficient. Bruna J allow a linear classifier to build class invariant on informative variability
22 Parameters&dimensionality of the Scattering 22 For 256x256 images, x 2 R 105 Yet it is possible to reduce it up to L x 2 R 2000 It depends on a few parameters of the mother wavelet L, J, the shape Identical parameters can be chosen for natural images on different datasets. It is a generic representation
23 23 J =3, 2{0, 4, 2, 3 4 } Order 2 Order 1 Order 0 g h g g g g h h h h x 3 x 0 x 1 x 2 Modulus h 0 Scattering coefficients are only at the output 2nd order Translation Scattering
24 Affine Scattering Transform Observe that W is covariant with the affine group Aff(E): 24 W [ ](g.x) = (g.x)? = W [g. ]x Ref.: PhD, L Sifre See W as a signal parametrised by some elements of the affine group: x? j, (u) = x(g),g =(u, r,j) We can define a WT on any compact Lie group(even not commutative) via: x? G (g) = Z G (g 0 )x(g 0 1.g)dg 0 Ref.: Topics in harmonic analysis related to the Littlewood-Paley theory Stein EM The same previous properties hold for this WT/Scattering. Ref.: Group Invariant Scattering, Mallat S
25 Separable Roto-Translation 25 Scattering Ref.: Deep Roto-Translation Scattering for Object Classification. EO and S Mallat Roto-translation group is not separable yet we used a separable wavelet transform on it. No averaging along angle (sensitivity increased) Separable (simple to implement and fast) Equal (slightly better) results as with non separable
26 26 J =3, 2{0, 4, 2, 3 4 } g h g g g g h h h h x 3 x 0 x 1 x 2 Separable convolution that Ref.: Deep Roto-Translation Scattering for Object Classification. EO and S Mallat recombines angles on 2nd order Separable Roto-Translation scattering
27 Linearization of the rotation Work in progress For a deformation: u (u) v (v)+(i r )(v)(u v) In fact the the affine group acts also on the deformation diffeomorphism: g.(i )(u) g.(i )(v)+g.(i r )(v)(u v) 27 Decompose it on the affine group: (I r )(v) =r (v)k(v) A way to linearize the action of the rotation? ksx Sx kapplec(kr k +...)
28 28 Classification pipeline x! x! L x! hl x, wi 0 Scattering Transform on YUV +Log Supervised dimensionality Reduction Gaussian SVM We learn L(select features) and w(select samples) from the data Getting L is the most costly part of the algorithm (Orthogonal Least Square)
29 29 Ref.: On the difference between orthogonal OLS? Supervised forward selection of features. The matching pursuit and orthogonal least squares. T. Blumensath and M. E. Davies. selection is done class per class. (similar to OMP) Principle: given a dictionary of feature { k } k Set y i =1ifi is in the class, 0 otherwise Find the most correlated feature k with y Pull it from the dictionary, orthogonalize the dictionary and normalize the dictionary. Select it. Iterate.
30 30 Dataset Type Paper Accuracy Caltech101 Scattering 79.9 Unsupervised Ask the locals 77.3 Numerical results RFL 75.3 M-HMP 82.5 Supervised DeepNet 91.4 Caltech256 Scattering 43.6 Unsupervised Ask the Locals 41.7 M-HMP 50.7 Supervised DeepNet 70.6 CIFAR10 Scattering 82.3 Unsupervised RFL 83.1 Supervised DeepNet 91.8 CIFAR100 Scattering 56.8 Unsupervised RFL 54.2 Supervised DeepNet 65.4 Identical Representation
31 31 Method Caltech101 CIFAR10 Translation Scattering order Translation Scattering order Translation Scattering order 2+ OLS Roto-translation Scattering order Roto-translation Scattering order 2+ OLS Improvement layer wise
32 32 How to fill in the Gap? Adding more supervision in the pipeline Building a DeepNet on top of it? Initialising a DeepNet with wavelets filters? Question is opened. A more complex classifier could help to handle class variabilities. Fisher vector with scattering? Adding a layer means identifying the next complex source of variabilities. Are they geometric? classes?
33 33 Other application of ST Audio Vincent Lostanlen Quantum chemistry Matthew Hirn Temporal data, video Reconstruction of WT Irène Waldspurger Unstructured data Mia Chen Xu Cheng
34 34 Conclusion We provide: Mathematical analysis and algorithms Competitive numerical results Software: (or send me an to get the latest!)
Image classification via Scattering Transform
1 Image classification via Scattering Transform Edouard Oyallon under the supervision of Stéphane Mallat following the work of Laurent Sifre, Joan Bruna, Classification of signals Let n>0, (X, Y ) 2 R
More informationInvariant Scattering Convolution Networks
Invariant Scattering Convolution Networks Joan Bruna and Stephane Mallat Submitted to PAMI, Feb. 2012 Presented by Bo Chen Other important related papers: [1] S. Mallat, A Theory for Multiresolution Signal
More informationQuantum Chemistry Energy Regression
Quantum Chemistry Energy Regression with Scattering Transforms Matthew Hirn, Stéphane Mallat École Normale Supérieure Nicolas Poilvert Penn-State 1 Quantum Chemistry Regression 2 Linear Regression 3 Energy
More informationarxiv: v2 [cs.cv] 30 May 2015
Deep Roto-Translation Scattering for Object Classification Edouard Oyallon and Stéphane Mallat Département Informatique, Ecole Normale Supérieure 45 rue d Ulm, 75005 Paris edouard.oyallon@ens.fr arxiv:1412.8659v2
More informationHarmonic Analysis of Deep Convolutional Neural Networks
Harmonic Analysis of Deep Convolutional Neural Networks Helmut Bőlcskei Department of Information Technology and Electrical Engineering October 2017 joint work with Thomas Wiatowski and Philipp Grohs ImageNet
More informationInvariant Scattering Convolution Networks
1 Invariant Scattering Convolution Networks Joan Bruna and Stéphane Mallat CMAP, Ecole Polytechnique, Palaiseau, France Abstract A wavelet scattering network computes a translation invariant image representation,
More informationRegML 2018 Class 8 Deep learning
RegML 2018 Class 8 Deep learning Lorenzo Rosasco UNIGE-MIT-IIT June 18, 2018 Supervised vs unsupervised learning? So far we have been thinking of learning schemes made in two steps f(x) = w, Φ(x) F, x
More informationTopics in Harmonic Analysis, Sparse Representations, and Data Analysis
Topics in Harmonic Analysis, Sparse Representations, and Data Analysis Norbert Wiener Center Department of Mathematics University of Maryland, College Park http://www.norbertwiener.umd.edu Thesis Defense,
More informationBuilding a Regular Decision Boundary with Deep Networks
Building a Regular Decision Boundary with Deep Networks Edouard Oyallon Département Informatique Ecole Normale Supérieure Paris, France edouard.oyallon@ens.fr Abstract In this work, we build a generic
More informationClassification of Hand-Written Digits Using Scattering Convolutional Network
Mid-year Progress Report Classification of Hand-Written Digits Using Scattering Convolutional Network Dongmian Zou Advisor: Professor Radu Balan Co-Advisor: Dr. Maneesh Singh (SRI) Background Overview
More informationSpatial Transformer Networks
BIL722 - Deep Learning for Computer Vision Spatial Transformer Networks Max Jaderberg Andrew Zisserman Karen Simonyan Koray Kavukcuoglu Contents Introduction to Spatial Transformers Related Works Spatial
More informationNeural networks and optimization
Neural networks and optimization Nicolas Le Roux Criteo 18/05/15 Nicolas Le Roux (Criteo) Neural networks and optimization 18/05/15 1 / 85 1 Introduction 2 Deep networks 3 Optimization 4 Convolutional
More informationClassification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses about the label (Top-5 error) No Bounding Box
ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton Motivation Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses
More informationGlobal Optimality in Matrix and Tensor Factorizations, Deep Learning and More
Global Optimality in Matrix and Tensor Factorizations, Deep Learning and More Ben Haeffele and René Vidal Center for Imaging Science Institute for Computational Medicine Learning Deep Image Feature Hierarchies
More informationSGD and Deep Learning
SGD and Deep Learning Subgradients Lets make the gradient cheating more formal. Recall that the gradient is the slope of the tangent. f(w 1 )+rf(w 1 ) (w w 1 ) Non differentiable case? w 1 Subgradients
More informationSTA 414/2104: Lecture 8
STA 414/2104: Lecture 8 6-7 March 2017: Continuous Latent Variable Models, Neural networks With thanks to Russ Salakhutdinov, Jimmy Ba and others Outline Continuous latent variable models Background PCA
More informationMulti-scale Geometric Summaries for Similarity-based Upstream S
Multi-scale Geometric Summaries for Similarity-based Upstream Sensor Fusion Duke University, ECE / Math 3/6/2019 Overall Goals / Design Choices Leverage multiple, heterogeneous modalities in identification
More informationDeep Learning: Approximation of Functions by Composition
Deep Learning: Approximation of Functions by Composition Zuowei Shen Department of Mathematics National University of Singapore Outline 1 A brief introduction of approximation theory 2 Deep learning: approximation
More informationMachine Learning for Signal Processing Neural Networks Continue. Instructor: Bhiksha Raj Slides by Najim Dehak 1 Dec 2016
Machine Learning for Signal Processing Neural Networks Continue Instructor: Bhiksha Raj Slides by Najim Dehak 1 Dec 2016 1 So what are neural networks?? Voice signal N.Net Transcription Image N.Net Text
More informationStable and Efficient Representation Learning with Nonnegativity Constraints. Tsung-Han Lin and H.T. Kung
Stable and Efficient Representation Learning with Nonnegativity Constraints Tsung-Han Lin and H.T. Kung Unsupervised Representation Learning Layer 3 Representation Encoding Sparse encoder Layer 2 Representation
More informationarxiv: v1 [cs.cv] 7 Mar 2014
Submitted to International Journal of Computer Vision manuscript No. (will be inserted by the editor) Rigid-Motion Scattering for Texture Classification Laurent Sifre Stéphane Mallat arxiv:1403.1687v1
More informationA HYBRID NETWORK: SCATTERING AND CONVNET
A HYBRID NETWORK: SCATTERING AND CONVNET Edouard Oyallon Département Informatique Ecole Normale Supérieure Paris, France edouard.oyallon@ens.fr ABSTRACT This paper shows how, by combining prior and supervised
More informationDeep Convolutional Neural Networks on Cartoon Functions
Deep Convolutional Neural Networks on Cartoon Functions Philipp Grohs, Thomas Wiatowski, and Helmut Bölcskei Dept. Math., ETH Zurich, Switzerland, and Dept. Math., University of Vienna, Austria Dept. IT
More informationWavelet Scattering Transforms
Wavelet Scattering Transforms Haixia Liu Department of Mathematics The Hong Kong University of Science and Technology February 6, 2018 Outline 1 Problem Dataset Problem two subproblems outline of image
More informationCheng Soon Ong & Christian Walder. Canberra February June 2018
Cheng Soon Ong & Christian Walder Research Group and College of Engineering and Computer Science Canberra February June 2018 Outlines Overview Introduction Linear Algebra Probability Linear Regression
More informationJakub Hajic Artificial Intelligence Seminar I
Jakub Hajic Artificial Intelligence Seminar I. 11. 11. 2014 Outline Key concepts Deep Belief Networks Convolutional Neural Networks A couple of questions Convolution Perceptron Feedforward Neural Network
More informationMachine Learning: Basis and Wavelet 김화평 (CSE ) Medical Image computing lab 서진근교수연구실 Haar DWT in 2 levels
Machine Learning: Basis and Wavelet 32 157 146 204 + + + + + - + - 김화평 (CSE ) Medical Image computing lab 서진근교수연구실 7 22 38 191 17 83 188 211 71 167 194 207 135 46 40-17 18 42 20 44 31 7 13-32 + + - - +
More informationDeep Learning of Invariant Spatiotemporal Features from Video. Bo Chen, Jo-Anne Ting, Ben Marlin, Nando de Freitas University of British Columbia
Deep Learning of Invariant Spatiotemporal Features from Video Bo Chen, Jo-Anne Ting, Ben Marlin, Nando de Freitas University of British Columbia Introduction Focus: Unsupervised feature extraction from
More informationFace Recognition. Face Recognition. Subspace-Based Face Recognition Algorithms. Application of Face Recognition
ace Recognition Identify person based on the appearance of face CSED441:Introduction to Computer Vision (2017) Lecture10: Subspace Methods and ace Recognition Bohyung Han CSE, POSTECH bhhan@postech.ac.kr
More informationWhat is semi-supervised learning?
What is semi-supervised learning? In many practical learning domains, there is a large supply of unlabeled data but limited labeled data, which can be expensive to generate text processing, video-indexing,
More informationCheng Soon Ong & Christian Walder. Canberra February June 2018
Cheng Soon Ong & Christian Walder Research Group and College of Engineering and Computer Science Canberra February June 2018 Outlines Overview Introduction Linear Algebra Probability Linear Regression
More informationTasks ADAS. Self Driving. Non-machine Learning. Traditional MLP. Machine-Learning based method. Supervised CNN. Methods. Deep-Learning based
UNDERSTANDING CNN ADAS Tasks Self Driving Localizati on Perception Planning/ Control Driver state Vehicle Diagnosis Smart factory Methods Traditional Deep-Learning based Non-machine Learning Machine-Learning
More informationCITS 4402 Computer Vision
CITS 4402 Computer Vision A/Prof Ajmal Mian Adj/A/Prof Mehdi Ravanbakhsh Lecture 06 Object Recognition Objectives To understand the concept of image based object recognition To learn how to match images
More informationLecture 7 Convolutional Neural Networks
Lecture 7 Convolutional Neural Networks CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor University of Chicago April 17, 2017 We saw before: ŷ x 1 x 2 x 3 x 4 A series of matrix multiplications:
More informationWhat Do Neural Networks Do? MLP Lecture 3 Multi-layer networks 1
What Do Neural Networks Do? MLP Lecture 3 Multi-layer networks 1 Multi-layer networks Steve Renals Machine Learning Practical MLP Lecture 3 7 October 2015 MLP Lecture 3 Multi-layer networks 2 What Do Single
More informationMULTISCALE SCATTERING FOR AUDIO CLASSIFICATION
MULTISCALE SCATTERING FOR AUDIO CLASSIFICATION Joakim Andén CMAP, Ecole Polytechnique, 91128 Palaiseau anden@cmappolytechniquefr Stéphane Mallat CMAP, Ecole Polytechnique, 91128 Palaiseau ABSTRACT Mel-frequency
More informationFeature Design. Feature Design. Feature Design. & Deep Learning
Artificial Intelligence and its applications Lecture 9 & Deep Learning Professor Daniel Yeung danyeung@ieee.org Dr. Patrick Chan patrickchan@ieee.org South China University of Technology, China Appropriately
More informationScattering.m Documentation
Scattering.m Documentation Release 0.3 Vincent Lostanlen Nov 04, 2018 Contents 1 Introduction 3 2 Filter bank specifications 5 3 Wavelets 7 Bibliography 9 i ii Scattering.m Documentation, Release 0.3
More informationLecture 13 Visual recognition
Lecture 13 Visual recognition Announcements Silvio Savarese Lecture 13-20-Feb-14 Lecture 13 Visual recognition Object classification bag of words models Discriminative methods Generative methods Object
More informationSajid Anwar, Kyuyeon Hwang and Wonyong Sung
Sajid Anwar, Kyuyeon Hwang and Wonyong Sung Department of Electrical and Computer Engineering Seoul National University Seoul, 08826 Korea Email: sajid@dsp.snu.ac.kr, khwang@dsp.snu.ac.kr, wysung@snu.ac.kr
More informationRAGAV VENKATESAN VIJETHA GATUPALLI BAOXIN LI NEURAL DATASET GENERALITY
RAGAV VENKATESAN VIJETHA GATUPALLI BAOXIN LI NEURAL DATASET GENERALITY SIFT HOG ALL ABOUT THE FEATURES DAISY GABOR AlexNet GoogleNet CONVOLUTIONAL NEURAL NETWORKS VGG-19 ResNet FEATURES COMES FROM DATA
More informationDeep Haar scattering networks
Information and Inference: A Journal of the IMA (2016) 5, 105 133 doi:10.1093/imaiai/iaw007 Advance Access publication on 19 April 2016 Deep Haar scattering networks Xiuyuan Cheng Applied Mathematics Program,
More informationDeep Learning: a gentle introduction
Deep Learning: a gentle introduction Jamal Atif jamal.atif@dauphine.fr PSL, Université Paris-Dauphine, LAMSADE February 8, 206 Jamal Atif (Université Paris-Dauphine) Deep Learning February 8, 206 / Why
More informationNeural Networks. Single-layer neural network. CSE 446: Machine Learning Emily Fox University of Washington March 10, /9/17
3/9/7 Neural Networks Emily Fox University of Washington March 0, 207 Slides adapted from Ali Farhadi (via Carlos Guestrin and Luke Zettlemoyer) Single-layer neural network 3/9/7 Perceptron as a neural
More informationDeep Learning (CNNs)
10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Deep Learning (CNNs) Deep Learning Readings: Murphy 28 Bishop - - HTF - - Mitchell
More informationDerived Distance: Beyond a model, towards a theory
Derived Distance: Beyond a model, towards a theory 9.520 April 23 2008 Jake Bouvrie work with Steve Smale, Tomaso Poggio, Andrea Caponnetto and Lorenzo Rosasco Reference: Smale, S., T. Poggio, A. Caponnetto,
More informationECE 521. Lecture 11 (not on midterm material) 13 February K-means clustering, Dimensionality reduction
ECE 521 Lecture 11 (not on midterm material) 13 February 2017 K-means clustering, Dimensionality reduction With thanks to Ruslan Salakhutdinov for an earlier version of the slides Overview K-means clustering
More informationApprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning
Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning Nicolas Thome Prenom.Nom@cnam.fr http://cedric.cnam.fr/vertigo/cours/ml2/ Département Informatique Conservatoire
More information<Special Topics in VLSI> Learning for Deep Neural Networks (Back-propagation)
Learning for Deep Neural Networks (Back-propagation) Outline Summary of Previous Standford Lecture Universal Approximation Theorem Inference vs Training Gradient Descent Back-Propagation
More informationOptical Character Recognition of Jutakshars within Devanagari Script
Optical Character Recognition of Jutakshars within Devanagari Script Sheallika Singh Shreesh Ladha Supervised by : Dr. Harish Karnick, Dr. Amit Mitra UGP Presentation, 10 April 2016 OCR of Jutakshars within
More informationStochastic Gradient Descent: The Workhorse of Machine Learning. CS6787 Lecture 1 Fall 2017
Stochastic Gradient Descent: The Workhorse of Machine Learning CS6787 Lecture 1 Fall 2017 Fundamentals of Machine Learning? Machine Learning in Practice this course What s missing in the basic stuff? Efficiency!
More informationIntelligent Systems Discriminative Learning, Neural Networks
Intelligent Systems Discriminative Learning, Neural Networks Carsten Rother, Dmitrij Schlesinger WS2014/2015, Outline 1. Discriminative learning 2. Neurons and linear classifiers: 1) Perceptron-Algorithm
More informationIntroduction to Convolutional Neural Networks 2018 / 02 / 23
Introduction to Convolutional Neural Networks 2018 / 02 / 23 Buzzword: CNN Convolutional neural networks (CNN, ConvNet) is a class of deep, feed-forward (not recurrent) artificial neural networks that
More informationUnsupervised Feature Learning from Temporal Data
Unsupervised Feature Learning from Temporal Data Rostislav Goroshin 1 goroshin@cims.nyu.edu Joan Bruna 1 bruna@cims.nyu.edu Jonathan Tompson 1 tompson@cims.nyu.edu Arthur Szlam 2 aszlam@ccny.cuny.edu David
More informationJOINT TIME-FREQUENCY SCATTERING FOR AUDIO CLASSIFICATION
2015 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, SEPT. 17 20, 2015, BOSTON, USA JOINT TIME-FREQUENCY SCATTERING FOR AUDIO CLASSIFICATION Joakim Andén PACM Princeton University,
More informationWhen Dictionary Learning Meets Classification
When Dictionary Learning Meets Classification Bufford, Teresa 1 Chen, Yuxin 2 Horning, Mitchell 3 Shee, Liberty 1 Mentor: Professor Yohann Tendero 1 UCLA 2 Dalhousie University 3 Harvey Mudd College August
More informationLinear Classifiers as Pattern Detectors
Intelligent Systems: Reasoning and Recognition James L. Crowley ENSIMAG 2 / MoSIG M1 Second Semester 2013/2014 Lesson 18 23 April 2014 Contents Linear Classifiers as Pattern Detectors Notation...2 Linear
More informationSIMPLE GABOR FEATURE SPACE FOR INVARIANT OBJECT RECOGNITION
SIMPLE GABOR FEATURE SPACE FOR INVARIANT OBJECT RECOGNITION Ville Kyrki Joni-Kristian Kamarainen Laboratory of Information Processing, Department of Information Technology, Lappeenranta University of Technology,
More informationMultiscale methods for neural image processing. Sohil Shah, Pallabi Ghosh, Larry S. Davis and Tom Goldstein Hao Li, Soham De, Zheng Xu, Hanan Samet
Multiscale methods for neural image processing Sohil Shah, Pallabi Ghosh, Larry S. Davis and Tom Goldstein Hao Li, Soham De, Zheng Xu, Hanan Samet A TALK IN TWO ACTS Part I: Stacked U-nets The globalization
More informationBrief Introduction of Machine Learning Techniques for Content Analysis
1 Brief Introduction of Machine Learning Techniques for Content Analysis Wei-Ta Chu 2008/11/20 Outline 2 Overview Gaussian Mixture Model (GMM) Hidden Markov Model (HMM) Support Vector Machine (SVM) Overview
More informationCSC321 Lecture 16: ResNets and Attention
CSC321 Lecture 16: ResNets and Attention Roger Grosse Roger Grosse CSC321 Lecture 16: ResNets and Attention 1 / 24 Overview Two topics for today: Topic 1: Deep Residual Networks (ResNets) This is the state-of-the
More informationHigher-order Statistical Modeling based Deep CNNs (Part-I)
Higher-order Statistical Modeling based Deep CNNs (Part-I) Classical Methods & From Shallow to Deep Qilong Wang 2018-11-23 Context 1 2 3 4 Higher-order Statistics in Bag-of-Visual-Words (BoVW) Higher-order
More informationLearning Methods for Linear Detectors
Intelligent Systems: Reasoning and Recognition James L. Crowley ENSIMAG 2 / MoSIG M1 Second Semester 2011/2012 Lesson 20 27 April 2012 Contents Learning Methods for Linear Detectors Learning Linear Detectors...2
More informationSTA 414/2104: Lecture 8
STA 414/2104: Lecture 8 6-7 March 2017: Continuous Latent Variable Models, Neural networks Delivered by Mark Ebden With thanks to Russ Salakhutdinov, Jimmy Ba and others Outline Continuous latent variable
More informationBACKPROPAGATION. Neural network training optimization problem. Deriving backpropagation
BACKPROPAGATION Neural network training optimization problem min J(w) w The application of gradient descent to this problem is called backpropagation. Backpropagation is gradient descent applied to J(w)
More informationarxiv: v1 [cs.lg] 25 Sep 2018
Utilizing Class Information for DNN Representation Shaping Daeyoung Choi and Wonjong Rhee Department of Transdisciplinary Studies Seoul National University Seoul, 08826, South Korea {choid, wrhee}@snu.ac.kr
More informationNeural Networks with Applications to Vision and Language. Feedforward Networks. Marco Kuhlmann
Neural Networks with Applications to Vision and Language Feedforward Networks Marco Kuhlmann Feedforward networks Linear separability x 2 x 2 0 1 0 1 0 0 x 1 1 0 x 1 linearly separable not linearly separable
More informationTwo at Once: Enhancing Learning and Generalization Capacities via IBN-Net
Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net Supplementary Material Xingang Pan 1, Ping Luo 1, Jianping Shi 2, and Xiaoou Tang 1 1 CUHK-SenseTime Joint Lab, The Chinese University
More informationDeep Neural Networks (1) Hidden layers; Back-propagation
Deep Neural Networs (1) Hidden layers; Bac-propagation Steve Renals Machine Learning Practical MLP Lecture 3 2 October 2018 http://www.inf.ed.ac.u/teaching/courses/mlp/ MLP Lecture 3 / 2 October 2018 Deep
More informationReview: Learning Bimodal Structures in Audio-Visual Data
Review: Learning Bimodal Structures in Audio-Visual Data CSE 704 : Readings in Joint Visual, Lingual and Physical Models and Inference Algorithms Suren Kumar Vision and Perceptual Machines Lab 106 Davis
More informationStatistical Machine Learning
Statistical Machine Learning Christoph Lampert Spring Semester 2015/2016 // Lecture 12 1 / 36 Unsupervised Learning Dimensionality Reduction 2 / 36 Dimensionality Reduction Given: data X = {x 1,..., x
More informationIntroduction to Machine Learning Midterm Exam
10-701 Introduction to Machine Learning Midterm Exam Instructors: Eric Xing, Ziv Bar-Joseph 17 November, 2015 There are 11 questions, for a total of 100 points. This exam is open book, open notes, but
More informationKernel Density Topic Models: Visual Topics Without Visual Words
Kernel Density Topic Models: Visual Topics Without Visual Words Konstantinos Rematas K.U. Leuven ESAT-iMinds krematas@esat.kuleuven.be Mario Fritz Max Planck Institute for Informatics mfrtiz@mpi-inf.mpg.de
More informationLecture 14: Deep Generative Learning
Generative Modeling CSED703R: Deep Learning for Visual Recognition (2017F) Lecture 14: Deep Generative Learning Density estimation Reconstructing probability density function using samples Bohyung Han
More informationNeural networks and optimization
Neural networks and optimization Nicolas Le Roux INRIA 8 Nov 2011 Nicolas Le Roux (INRIA) Neural networks and optimization 8 Nov 2011 1 / 80 1 Introduction 2 Linear classifier 3 Convolutional neural networks
More informationMachine Learning. Support Vector Machines. Manfred Huber
Machine Learning Support Vector Machines Manfred Huber 2015 1 Support Vector Machines Both logistic regression and linear discriminant analysis learn a linear discriminant function to separate the data
More informationImproved Local Coordinate Coding using Local Tangents
Improved Local Coordinate Coding using Local Tangents Kai Yu NEC Laboratories America, 10081 N. Wolfe Road, Cupertino, CA 95129 Tong Zhang Rutgers University, 110 Frelinghuysen Road, Piscataway, NJ 08854
More informationIntroduction to Mathematical Programming
Introduction to Mathematical Programming Ming Zhong Lecture 25 November 5, 2018 Ming Zhong (JHU) AMS Fall 2018 1 / 19 Table of Contents 1 Ming Zhong (JHU) AMS Fall 2018 2 / 19 Some Preliminaries: Fourier
More informationNormalization Techniques in Training of Deep Neural Networks
Normalization Techniques in Training of Deep Neural Networks Lei Huang ( 黄雷 ) State Key Laboratory of Software Development Environment, Beihang University Mail:huanglei@nlsde.buaa.edu.cn August 17 th,
More informationIs Robustness the Cost of Accuracy? A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
Is Robustness the Cost of Accuracy? A Comprehensive Study on the Robustness of 18 Deep Image Classification Models Dong Su 1*, Huan Zhang 2*, Hongge Chen 3, Jinfeng Yi 4, Pin-Yu Chen 1, and Yupeng Gao
More informationMultimodal context analysis and prediction
Multimodal context analysis and prediction Valeria Tomaselli (valeria.tomaselli@st.com) Sebastiano Battiato Giovanni Maria Farinella Tiziana Rotondo (PhD student) Outline 2 Context analysis vs prediction
More informationDimensionality Reduction
Dimensionality Reduction Le Song Machine Learning I CSE 674, Fall 23 Unsupervised learning Learning from raw (unlabeled, unannotated, etc) data, as opposed to supervised data where a classification of
More informationMachine learning comes from Bayesian decision theory in statistics. There we want to minimize the expected value of the loss function.
Bayesian learning: Machine learning comes from Bayesian decision theory in statistics. There we want to minimize the expected value of the loss function. Let y be the true label and y be the predicted
More informationTheories of Deep Learning
Theories of Deep Learning Lecture 02 Donoho, Monajemi, Papyan Department of Statistics Stanford Oct. 4, 2017 1 / 50 Stats 385 Fall 2017 2 / 50 Stats 285 Fall 2017 3 / 50 Course info Wed 3:00-4:20 PM in
More informationMulti-Layer Boosting for Pattern Recognition
Multi-Layer Boosting for Pattern Recognition François Fleuret IDIAP Research Institute, Centre du Parc, P.O. Box 592 1920 Martigny, Switzerland fleuret@idiap.ch Abstract We extend the standard boosting
More informationWavelet-based Salient Points with Scale Information for Classification
Wavelet-based Salient Points with Scale Information for Classification Alexandra Teynor and Hans Burkhardt Department of Computer Science, Albert-Ludwigs-Universität Freiburg, Germany {teynor, Hans.Burkhardt}@informatik.uni-freiburg.de
More informationDynamic Data Modeling, Recognition, and Synthesis. Rui Zhao Thesis Defense Advisor: Professor Qiang Ji
Dynamic Data Modeling, Recognition, and Synthesis Rui Zhao Thesis Defense Advisor: Professor Qiang Ji Contents Introduction Related Work Dynamic Data Modeling & Analysis Temporal localization Insufficient
More informationEE 6882 Visual Search Engine
EE 6882 Visual Search Engine Prof. Shih Fu Chang, Feb. 13 th 2012 Lecture #4 Local Feature Matching Bag of Word image representation: coding and pooling (Many slides from A. Efors, W. Freeman, C. Kambhamettu,
More informationModularity Matters: Learning Invariant Relational Reasoning Tasks
Summer Review 3 Modularity Matters: Learning Invariant Relational Reasoning Tasks Jason Jo 1, Vikas Verma 2, Yoshua Bengio 1 1: MILA, Universit de Montral 2: Department of Computer Science Aalto University,
More informationCS5670: Computer Vision
CS5670: Computer Vision Noah Snavely Lecture 5: Feature descriptors and matching Szeliski: 4.1 Reading Announcements Project 1 Artifacts due tomorrow, Friday 2/17, at 11:59pm Project 2 will be released
More informationGroup Equivariant Convolutional Networks. Taco Cohen
Group Equivariant Convolutional Networks Taco Cohen Outline 1. Symmetry & Deep Learning: Statistical Power from Symmetry Invariance vs Equivariance Equivariance in Deep Learning 2.Group Theory Symmetry,
More informationGlobal Optimality in Matrix and Tensor Factorization, Deep Learning & Beyond
Global Optimality in Matrix and Tensor Factorization, Deep Learning & Beyond Ben Haeffele and René Vidal Center for Imaging Science Mathematical Institute for Data Science Johns Hopkins University This
More informationNeural Networks. Nicholas Ruozzi University of Texas at Dallas
Neural Networks Nicholas Ruozzi University of Texas at Dallas Handwritten Digit Recognition Given a collection of handwritten digits and their corresponding labels, we d like to be able to correctly classify
More informationTensor Methods for Feature Learning
Tensor Methods for Feature Learning Anima Anandkumar U.C. Irvine Feature Learning For Efficient Classification Find good transformations of input for improved classification Figures used attributed to
More informationOverview. Introduction to local features. Harris interest points + SSD, ZNCC, SIFT. Evaluation and comparison of different detectors
Overview Introduction to local features Harris interest points + SSD, ZNCC, SIFT Scale & affine invariant interest point detectors Evaluation and comparison of different detectors Region descriptors and
More informationTUTORIAL PART 1 Unsupervised Learning
TUTORIAL PART 1 Unsupervised Learning Marc'Aurelio Ranzato Department of Computer Science Univ. of Toronto ranzato@cs.toronto.edu Co-organizers: Honglak Lee, Yoshua Bengio, Geoff Hinton, Yann LeCun, Andrew
More informationMaxout Networks. Hien Quoc Dang
Maxout Networks Hien Quoc Dang Outline Introduction Maxout Networks Description A Universal Approximator & Proof Experiments with Maxout Why does Maxout work? Conclusion 10/12/13 Hien Quoc Dang Machine
More informationOBJECT DETECTION AND RECOGNITION IN DIGITAL IMAGES
OBJECT DETECTION AND RECOGNITION IN DIGITAL IMAGES THEORY AND PRACTICE Bogustaw Cyganek AGH University of Science and Technology, Poland WILEY A John Wiley &. Sons, Ltd., Publication Contents Preface Acknowledgements
More informationFisher Vector image representation
Fisher Vector image representation Machine Learning and Category Representation 2014-2015 Jakob Verbeek, January 9, 2015 Course website: http://lear.inrialpes.fr/~verbeek/mlcr.14.15 A brief recap on kernel
More informationCompressing the Input for CNNs with the First-Order Scattering Transform
Compressing the Input for CNNs with the First-Order Scattering Transform Edouard Oyallon, 1,4,5 Eugene Belilovsky, 2 Sergey Zagoruyko, 3 Michal Valko 4 1 CentraleSupelec, Université Paris-Saclay 2 MILA,
More information