Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.22075 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915417105104896 |
|---|---|
| author | Ali, Eman Arora, Chetan Khan, Muhammad Haris |
| author_facet | Ali, Eman Arora, Chetan Khan, Muhammad Haris |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_22075 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Prototype-Guided Pseudo-Labeling with Neighborhood-Aware Consistency for Unsupervised Adaptation Ali, Eman Arora, Chetan Khan, Muhammad Haris Machine Learning 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. |
| title | Prototype-Guided Pseudo-Labeling with Neighborhood-Aware Consistency for Unsupervised Adaptation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.22075 |