Vocabulary-Incomplete Unsupervised Vision-Language Model Adaptation
arXiv:2610.23919v1 Announce Type: new Abstract: In certain real-world scenarios, obtaining labeled data is excessively expensive, motivating increasing interest in adapting models without annotations. Vision-language models (VLMs) provide pseudo-labels for unlabeled images through image-text simila…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-20 04:00 · arXiv cs.CV
Vocabulary-Incomplete Unsupervised Vision-Language Model Adaptation