{"ID":2891952,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.22075","arxiv_id":"2507.22075","title":"Prototype-Guided Pseudo-Labeling with Neighborhood-Aware Consistency for Unsupervised Adaptation","abstract":"In unsupervised adaptation for vision-language models such as CLIP, pseudo-labels derived from zero-shot predictions often exhibit significant noise, particularly under domain shifts or in visually complex scenarios. Conventional pseudo-label filtering approaches, which rely on fixed confidence thresholds, tend to be unreliable in fully unsupervised settings. In this work, we propose a novel adaptive pseudo-labeling framework that enhances CLIP's adaptation performance by integrating prototype consistency and neighborhood-based consistency. The proposed method comprises two key components: PICS, which assesses pseudo-label accuracy based on in-class feature compactness and cross-class feature separation; and NALR, which exploits semantic similarities among neighboring samples to refine pseudo-labels dynamically. Additionally, we introduce an adaptive weighting mechanism that adjusts the influence of pseudo-labeled samples during training according to their estimated correctness. Extensive experiments on 11 benchmark datasets demonstrate that our method achieves state-of-the-art performance in unsupervised adaptation scenarios, delivering more accurate pseudo-labels while maintaining computational efficiency.","short_abstract":"In unsupervised adaptation for vision-language models such as CLIP, pseudo-labels derived from zero-shot predictions often exhibit significant noise, particularly under domain shifts or in visually complex scenarios. Conventional pseudo-label filtering approaches, which rely on fixed confidence thresholds, tend to be u...","url_abs":"https://arxiv.org/abs/2507.22075","url_pdf":"https://arxiv.org/pdf/2507.22075v1","authors":"[\"Eman Ali\",\"Chetan Arora\",\"Muhammad Haris Khan\"]","published":"2025-07-22T19:08:24Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Language Model\"]","has_code":false}