SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.05671 · ICCV · 2021

Shape-Biased Domain Generalization via Shock Graph Embeddings

Benjamin Kimia, Maruthi Narayanan, Vickram Rajendran

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.

Abstract

There is an emerging sense that the vulnerability of Image Convolutional Neural Networks (CNN), i.e., sensitivity to image corruptions, perturbations, and adversarial attacks, is connected with Texture Bias. This relative lack of Shape Bias is also responsible for poor performance in Domain Generalization (DG). The inclusion of a role of shape alleviates these vulnerabilities and some approaches have achieved this by training on negative images, images endowed with edge maps, or images with conflicting shape and texture information. This paper advocates an explicit and complete representation of shape using a classical computer vision approach, namely, representing the shape content of an image with the shock graph of its contour map. The resulting graph and its descriptor is a complete representation of contour content and is classified using recent Graph Neural Network (GNN) methods. The experimental results on three domain shift datasets, Colored MNIST, PACS, and VLCS demonstrate that even without using appearance the shape-based approach exceeds classical Image CNN based methods in domain generalization.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2109.05671")
get_code_for_paper("2109.05671")
have("2109.05671")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2109.05671.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2109.05671.svg)](https://syntology.ai/paper/2109.05671)

Connect an agent — have() is free.