Reproduce “Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Haotian Zheng, Qizhou Wang, Zhen Fang, Xiaobo Xia, Feng Liu, Tongliang Liu, Bo Han

ATOL addresses open-world image classification by using generated data in an auxiliary in-distribution/out-of-distribution task, rather than assuming generated outliers are reliable. It separates auxiliary groups in latent space, regularizes the generator, and aligns auxiliary in-distribution features with real examples. On CIFAR-10, it averages 14.66% FPR95 and 97.05% AUROC across six OOD test sets; this is not a universal guarantee.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.