Image Background Serves as Good Proxy for Out-of-distribution Data

TL;DR

This paper introduces SSOD, a novel OOD detection method that leverages natural signals from in-distribution data without needing explicit OOD samples, achieving state-of-the-art results across multiple benchmarks.

Contribution

It presents a unified probabilistic framework for OOD detection and proposes SSOD, an OOD-data-free model that exploits natural signals for improved detection performance.

Findings

SSOD outperforms previous methods on ImageNet and CIFAR-10 benchmarks.

Achieves significant reductions in false positive rates (FPR95).

Attains top performance on challenging OOD datasets like ImageNet-O.

Abstract

Out-of-distribution (OOD) detection empowers the model trained on the closed image set to identify unknown data in the open world. Though many prior techniques have yielded considerable improvements in this research direction, two crucial obstacles still remain. Firstly, a unified perspective has yet to be presented to view the developed arts with individual designs, which is vital for providing insights into future work. Secondly, we expect sufficient natural OOD supervision to promote the generation of compact boundaries between the in-distribution (ID) and OOD data without collecting explicit OOD samples. To tackle these issues, we propose a general probabilistic framework to interpret many existing methods and an OOD-data-free model, namely \textbf{S}elf-supervised \textbf{S}ampling for \textbf{O}OD \textbf{D}etection (SSOD). SSOD efficiently exploits natural OOD signals from the ID data based on the local property of convolution. With these supervisions, it jointly optimizes the OOD detection and conventional ID classification in an end-to-end manner. Extensive experiments reveal that SSOD establishes competitive state-of-the-art performance on many large-scale benchmarks, outperforming the best previous method by a large margin, \eg, reporting \textbf{-6.28\%} FPR95 and \textbf{+0.77\%} AUROC on ImageNet, \textbf{-19.01\%} FPR95 and \textbf{+3.04\%} AUROC on CIFAR-10, and top-ranked performance on hard OOD datasets, \ie, ImageNet-O and OpenImage-O.