Metraipolis › archive › dc_de3120dfe2bb

Progressive Subset Selection and Cascaded Consistency for Unsupervised Vision-Language Model Adaptation — arXiv:2610.27515

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.27515
License (as archived)
CC0-1.0
Archived
2026-10-21T07:07:48.998Z
SHA-256 of the archived text
9704166602994e92e5867661c9ebf67c024463981c00cc85a966522f334128bb
Stable URL of this page
https://metraipolis.com/documento/dc_de3120dfe2bb

How to cite

Progressive Subset Selection and Cascaded Consistency for Unsupervised Vision-Language Model Adaptation — arXiv:2610.27515 — arXiv (en), https://arxiv.org/abs/2610.27515 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_de3120dfe2bb (Metraipolis archive dc_de3120dfe2bb, sha256 9704166602994e92e5867661c9ebf67c024463981c00cc85a966522f334128bb)
BibTeX
@misc{dcde3120dfe2bb,
  title = {Progressive Subset Selection and Cascaded Consistency for Unsupervised Vision-Language Model Adaptation — arXiv:2610.27515},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.27515},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_de3120dfe2bb; sha256 9704166602994e92e5867661c9ebf67c024463981c00cc85a966522f334128bb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27515. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pretrained Vision-Language Models (PVLMs) achieve strong zero-shot recognition but often suffer performance degradation under target-domain shift. Unsupervised adaptation provides a practical way to improve target-domain performance without labeled data, but it remains challenging because pseudo-labels generated by the model can be unreliable and no labeled validation set is available for model selection or early stopping. We propose a simple framework for unsupervised PVLM adaptation that combines progressive margin-based subset selection with cascaded consistency learning. The subset selection strategy constructs a class-balanced pseudo-labeled set using prediction margins and gradually expands it during training, enabling adaptation to start from reliable supervision anchors before incorporating broader target-domain data. Cascaded consistency learning further exploits unlabeled samples by using temporally smoothed teacher predictions on weakly augmented views to supervise student predictions on strongly augmented views, with confidence filtering to reduce the influence of uncertain pseudo-labels. To preserve the pretrained embedding structure, the framework updates only normalization parameters in the visual encoder and class prototypes initialized from text prompts. Experiments across multiple recognition benchmarks with both CLIP and SigLIP backbones show consistent improvements over zero-shot baselines and competitive performance against recent unsupervised PVLM adaptation methods. These results suggest that progressive pseudo-label selection and teacher-guided consistency provide an effective and lightweight strategy for adapting PVLM classifiers without labeled target data.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.27515 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-21T07:05:43.567Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).