SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.03066 · ICCV · 2021

Distributional Robustness Loss for Long-tail Learning

Gal Chechik, Dvir Samuel

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

Real-world data is often unbalanced and long-tailed, but deep models struggle to recognize rare classes in the presence of frequent classes. To address unbalanced data, most studies try balancing the data, the loss, or the classifier to reduce classification bias towards head classes. Far less attention has been given to the latent representations learned with unbalanced data. We show that the feature extractor part of deep networks suffers greatly from this bias. We propose a new loss based on robustness theory, which encourages the model to learn high-quality representations for both head and tail classes. While the general form of the robustness loss may be hard to compute, we further derive an easy-to-compute upper bound that can be minimized efficiently. This procedure reduces representation bias towards head classes in the feature space and achieves new SOTA results on CIFAR100-LT, ImageNet-LT, and iNaturalist long-tail benchmarks. We find that training with robustness increases recognition accuracy of tail classes while largely maintaining the accuracy of head classes. The new robustness loss can be combined with various classifier balancing techniques and can be applied to representations at several layers of the deep model.

For agents

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

get_harvested_code_for_paper("2104.03066")
get_code_for_paper("2104.03066")
have("2104.03066")

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

curl https://syntology.ai/api/ran/2104.03066.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.03066.svg)](https://syntology.ai/paper/2104.03066)

Connect an agent — have() is free.