SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.09117 · ICLR · 2023

Part-Based Models Improve Adversarial Robustness

Nicholas Carlini, Chawin Sitawarin, David Wagner, Kornrapat Pongmala, Yizheng Chen

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. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We show that combining human prior knowledge with end-to-end learning can improve the robustness of deep neural networks by introducing a part-based model for object classification. We believe that the richer form of annotation helps guide neural networks to learn more robust features without requiring more samples or larger models. Our model combines a part segmentation model with a tiny classifier and is trained end-to-end to simultaneously segment objects into parts and then classify the segmented object. Empirically, our part-based models achieve both higher accuracy and higher adversarial robustness than a ResNet-50 baseline on all three datasets. For instance, the clean accuracy of our part models is up to 15 percentage points higher than the baseline's, given the same level of robustness. Our experiments indicate that these models also reduce texture bias and yield better robustness against common corruptions and spurious correlations. The code is publicly available at https://github.com/chawins/adv-part-model.

For agents

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

get_harvested_code_for_paper("2209.09117")
get_code_for_paper("2209.09117")
have("2209.09117")

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

curl https://syntology.ai/api/ran/2209.09117.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.09117.svg)](https://syntology.ai/paper/2209.09117)

Connect an agent — have() is free.