TINS: Test-time ID-prototype-separated Negative Semantics Learning for OOD Detection

TL;DR

TINS introduces a test-time method that learns sample-specific negative semantics for improved out-of-distribution detection in vision-language models, addressing limitations of static negative labels.

Contribution

The paper proposes TINS, a novel test-time approach that learns and regularizes negative semantics dynamically, enhancing OOD detection performance over existing static methods.

Findings

TINS significantly reduces FPR95 on Four-OOD benchmark from 14.04% to 6.72%.

Extensive experiments show consistent improvements across multiple OOD detection benchmarks.

The method effectively stabilizes negative semantics expansion through group-wise aggregation and buffer updates.

Abstract

Vision-language models enable OOD detection by comparing image alignment with ID labels and negative semantics. Existing negative-label-based methods mainly rely on static negative labels constructed before inference, limiting their ability to cover diverse and evolving OOD concepts. Although test-time expansion provides a natural solution, naively learning negative semantics from potential OOD samples may introduce hard ID contamination. To address this issue, we propose a \textbf{T}est-time \textbf{I}D-prototype-separated \textbf{N}egative \textbf{S}emantics learning method, termed \textbf{TINS}. TINS learns sample-specific negative text embeddings via image-to-text modality inversion and introduces ID-prototype-separated regularization to keep them separated from ID semantics. To further stabilize negative semantics expansion, TINS employs group-wise aggregation scoring and a buffer update strategy. Extensive experiments across Four-OOD, OpenOOD, Temporal-shift, and Various ID settings show consistent improvements over strong baselines. Notably, on the Four-OOD benchmark with ImageNet-1K as ID, TINS reduces the average FPR95 from 14.04\% to 6.72\%. Our code is available at https://github.com/zxk1212/tins.