Lecture 14 Convolutional Neural Networks on Surfaces via
- Slides: 27
Lecture 14: Convolutional Neural Networks on Surfaces via Seamless Toric Covers Jiacheng Cheng Feb, 21, 2018
Convolutional neural networkson surfaces via seamless toric covers Haggai Maron, Meirav Galun, Noam Aigerman, Miri Trope, Nadav Dym, Ersin Yumer, Vladimir G. Kim, Yaron Lipman Jiacheng Cheng Lecture 14
Problem statement Easy Jiacheng Cheng Lecture 14 Hard
Deep Learning Geometric Deep Learning Jiacheng Cheng Lecture 14
What is required to define a CNN? Jiacheng Cheng Lecture 14
• Translations Two dimensional, commutative Isometries of R^2 • Convolution Linear Translation invariant • Pooling Non-linear (max) Sub-translation invariant Jiacheng Cheng Lecture 14
Defining CNNs on surfaces Jiacheng Cheng Lecture 14
Translations on surfaces? • Translation on surface ≝ locally Euclidean translation • Flow along non-vanishing vector fields Jiacheng Cheng Lecture 14
Flat torus! • Translations “modulo 1” • Full translation invariance on the flat torus ! Jiacheng Cheng Lecture 14
Only the torus! Index Euler of vector field characteristic • Poincaré-Hopf: For a compact orientable surface • Index – a measure of the complexity near a vanishing point • Non-vanishing vector field implies genus 1 - torus Jiacheng Cheng Lecture 14
15 CNN on flat torus Cyclic padding Jiacheng Cheng Lecture 14
16 Recap • CNN is well-defined over flat-torus • Roadblocks for CNN on sphere-type surfaces • Topological: No locally Euclidean translations on spheres • Geometrical: The flat torus is flat and our surface is not Jiacheng Cheng Lecture 14
17 Solution: Map the surface to a flat torus Jiacheng Cheng Lecture 14
Torus 4 -cover ≅ Jiacheng Cheng Lecture 14
19 Mapping the Torus to the flat Torus ! Aigerman and Lipman, 2015 Jiacheng Cheng Lecture 14
The pull back translation ! Jiacheng Cheng Lecture 14
22 Pull-back Translations: pull-back Euclidean translations Two dimensional, commutative Conformal maps Pull-back convolution Linear Theorem: Translation invariance Pull-back pooling Non-linear (max) Sub-translation invariant Jiacheng Cheng Lecture 14 !
24 New layers cyclic padding Jiacheng Cheng Lecture 14 projection
Data generation Input image Jiacheng Cheng Lecture 14 Labels
26 Testphase • Aggregation from differenttriplets • “Magnifying glass” • Scale factor as weights + Jiacheng Cheng Lecture 14 + + =
27 Human bodysegmentation Train: 370 models FAUST, MIT, SCAPE, ADOBE Jiacheng Cheng Lecture 14 Test: 18 models SHREC 07
Easy functions Raw • Normals • Average geodesic distance • Wave kernel signature Jiacheng Cheng Lecture 14 Complex
Human bodysegmentation Train: 370 models FAUST, MIT, SCAPE, ADOBE Jiacheng Cheng Lecture 14 Test: 18 models SHREC 07
CNN applied to other data Jiacheng Cheng Lecture 14
Biological landmarksdetection • Train: 73 teeth from BOYER • Only curvature and scale factor Test: 8 teeth from BOYER Jiacheng Cheng Lecture 14
32 Biological landmarks Jiacheng Cheng Lecture 14
35 Conclusion • CNN of sphere-typesurfaces • We defined a meaningful convolution on surfaces • Learns from rawfeatures • Reusing CNN software for images Limitations and future work Scope: Only sphere type surfaces • No canonical choice for triplets (and convolutions) • Learn aggregation operator • Jiacheng Cheng Lecture 14
- Convolutional neural networks
- Visualizing and understanding convolutional networks
- Csrmm
- Convolutional neural network alternatives
- Convolutional neural networks for visual recognition
- Introduction to convolutional neural networks
- Leon gatys
- Convolutional neural networks
- Cnn ppt
- Convolutional neural network
- Convolutional deep belief networks
- Image super resolution using deep convolutional networks
- Superpixel segmentation with fully convolutional networks
- Deep convolutional networks
- Modeling relational data with graph convolutional networks
- Graph neural network lecture
- The wake-sleep algorithm for unsupervised neural networks
- Neural networks simon haykin
- Nvdla
- Andrew ng rnn
- Newff matlab
- Vc dimension neural network
- Bharath subramanyam
- On the computational efficiency of training neural networks
- Few shot learning with graph neural networks
- Deep neural networks and mixed integer linear optimization
- Predicting nba games using neural networks
- Neural networks for rf and microwave design