# Distributionally Robust Classification on a Data Budget

Source: [Distributionally Robust Classification on a Data Budget](<https://www.sota2.com/research/paper/68fa70451e209131cea4a148>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:25:24.889Z

Authors: Benjamin Feuer, Ameya Joshi, Minh Pham, Chinmay Hegde

Published: 2023-08-07T15:30:02.000Z

## Abstract

Real world uses of deep learning require predictable model behavior under distribution shifts. Models such as CLIP show emergent natural distributional robustness comparable to humans, but may require hundreds of millions of training samples. Can we train robust learners in a domain where data is limited? To rigorously address this question, we introduce JANuS (Joint Annotations and Names Set), a collection of four new training datasets with images, labels, and corresponding captions, and perform a series of carefully controlled investigations of factors contributing to robustness in image classification, then compare those results to findings derived from a large-scale meta-analysis. Using this approach, we show that standard ResNet-50 trained with the cross-entropy loss on 2.4 million image samples can attain comparable robustness to a CLIP ResNet-50 trained on 400 million samples. To our knowledge, this is the first result showing (near) state-of-the-art distributional robustness on limited data budgets. Our dataset is available at \\url{https://huggingface.co/datasets/penfever/JANuS\_dataset}, and the code used to reproduce our experiments can be found at \\url{https://github.com/penfever/vlhub/}.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2308.03821>)

[PDF](<https://arxiv.org/pdf/2308.03821.pdf>)
