Shape-Tailored Deep Neural Networks

by   Naeemullah Khan, et al.

We present Shape-Tailored Deep Neural Networks (ST-DNN). ST-DNN extend convolutional networks (CNN), which aggregate data from fixed shape (square) neighborhoods, to compute descriptors defined on arbitrarily shaped regions. This is natural for segmentation, where descriptors should describe regions (e.g., of objects) that have diverse shape. We formulate these descriptors through the Poisson partial differential equation (PDE), which can be used to generalize convolution to arbitrary regions. We stack multiple PDE layers to generalize a deep CNN to arbitrary regions, and apply it to segmentation. We show that ST-DNN are covariant to translations and rotations and robust to domain deformations, natural for segmentation, which existing CNN based methods lack. ST-DNN are 3-4 orders of magnitude smaller then CNNs used for segmentation. We show that they exceed segmentation performance compared to state-of-the-art CNN-based descriptors using 2-3 orders smaller training sets on the texture segmentation problem.



There are no comments yet.


page 8

page 21

page 23

page 24

page 25

page 26

page 27

page 29


Compression of Deep Neural Networks for Image Instance Retrieval

Image instance retrieval is the problem of retrieving images from a data...

Structured 2D Representation of 3D Data for Shape Processing

We represent 3D shape by structured 2D representations of fixed length m...

Deep Neural Networks motivated by Partial Differential Equations

Partial differential equations (PDEs) are indispensable for modeling man...

Brain Tumor Segmentation with Deep Neural Networks

In this paper, we present a fully automatic brain tumor segmentation met...

Shape-Biased Domain Generalization via Shock Graph Embeddings

There is an emerging sense that the vulnerability of Image Convolutional...

CNN-based Prostate Zonal Segmentation on T2-weighted MR Images: A Cross-dataset Study

Prostate cancer is the most common cancer among US men. However, prostat...

Geodesic convolutional neural networks on Riemannian manifolds

Feature descriptors play a crucial role in a wide range of geometry anal...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.