TINS method enhances OOD detection in vision-language models

Researchers have developed TINS, a novel method for Out-of-Distribution (OOD) detection in vision-language models. TINS addresses limitations of static negative labels by learning dynamic negative semantics during test-time inference. It employs image-to-text modality inversion and an ID-prototype-separated regularization to prevent contamination from in-distribution concepts. Experiments show significant improvements, such as reducing FPR95 from 14.04% to 6.72% on the Four-OOD benchmark. AI

IMPACT Improves the ability of vision-language models to identify novel or unexpected data, crucial for robust AI deployment.

RANK_REASON Publication of a new academic paper detailing a novel method for OOD detection. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• Four-OOD benchmark
• vision-language models
• ImageNet-1K

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →