paper-with-me

홈 › Papers

Distributionally Robust Classification on a Data Budget

2023-08-07 · Benjamin Feuer, Ameya Joshi, Minh Pham, Chinmay Hegde

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/}.

📄 PDF Abstract BibTeX arXiv:2308.03821

Code (1)

penfever/vlhub 공식 구현 pytorch

Tasks

Classificationimage-classificationImage ClassificationRobust classification

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Distributionally Robust Self Paced Curriculum Reinforcement Learning

2025-11-07 · Anirudh Satheesh, Keenan Powell, Vaneet Aggarwal arxiv

A central challenge in reinforcement learning is that policies trained in controlled environments often fail under distribution shifts at deployment into real-world environments. Distributionally Robust Reinforcement Lea…

Reinforcement Learning

Distributionally-Robust Machine Learning Using Locally Differentially-Private Data

2020-06-24 · Farhad Farokhi

We consider machine learning, particularly regression, using locally-differentially private datasets. The Wasserstein distance is used to define an ambiguity set centered at the empirical distribution of the dataset corr…

BIG-bench Machine Learningregression

Distributionally Robust Constrained Reinforcement Learning under Strong Duality

2024-06-22 · Zhengfei Zhang, Kishan Panaganti, Laixi Shi, Yanan Sui 외

We study the problem of Distributionally Robust Constrained RL (DRC-RL), where the goal is to maximize the expected reward subject to environmental distribution shifts and constraints. This setting captures situations wh…

Car Racingreinforcement-learningReinforcement Learning

Conservative neural posterior estimation via distributionally robust training

2026-05-27 · William Laplante, Yuga Hikida, Charita Dellaporta, François-Xavier Briol 외 arxiv

Simulation-based inference with neural posterior estimation (NPE) often yields overconfident and unreliable posteriors under limited simulation budgets. To address this, we propose DRO-NPE, a distributionally robust appr…

ODIST: Open World Classification via Distributionally Shifted Instances

2021-11-01 · Findings (EMNLP) 2021 11 · Lei Shu, Yassine Benajiba, Saab Mansour, Yi Zhang

In this work, we address the open-world classification problem with a method called ODIST, open world classification via distributionally shifted instances. This novel and straightforward method can create out-of-domain …

ClassificationLanguage ModelingLanguage Modelling