The 8088 The 8088 ← All news
arXiv cs.CL AI Research Apr 20

TTL: Test-time Textual Learning for OOD Detection with Pretrained Vision-Language Models

★★★★★ significance 2/5

Researchers introduce Test-time Textual Learning (TTL), a framework designed to improve Out-of-distribution (OOD) detection in vision-language models. The method uses pseudo-labeled test samples and a knowledge bank to dynamically learn new semantic information without needing fixed external labels.

Why it matters Dynamic adaptation to evolving semantic spaces addresses a critical reliability gap in deploying vision-language models in unpredictable, real-world environments.
Read the original at arXiv cs.CL

Tags

#vision-language models #ood detection #test-time adaptation #clip #machine learning

Related coverage