Metraipolis › archive › dc_d207bb4b0e5d

Towards Continual Test-Time Adaptation of Vision-Language Models in Open-Vocabulary Semantic Segmentation — arXiv:2608.29923

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29923
License (as archived)
CC0-1.0
Archived
2026-10-17T08:39:53.453Z
SHA-256 of the archived text
9128217e948aa2384f4adc3a94b255585a8dd4e6d476246afe28243772746e2e
Stable URL of this page
https://metraipolis.com/documento/dc_d207bb4b0e5d

How to cite

Towards Continual Test-Time Adaptation of Vision-Language Models in Open-Vocabulary Semantic Segmentation — arXiv:2608.29923 — arXiv (en), https://arxiv.org/abs/2608.29923 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d207bb4b0e5d (Metraipolis archive dc_d207bb4b0e5d, sha256 9128217e948aa2384f4adc3a94b255585a8dd4e6d476246afe28243772746e2e)
BibTeX
@misc{dcd207bb4b0e5d,
  title = {Towards Continual Test-Time Adaptation of Vision-Language Models in Open-Vocabulary Semantic Segmentation — arXiv:2608.29923},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29923},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d207bb4b0e5d; sha256 9128217e948aa2384f4adc3a94b255585a8dd4e6d476246afe28243772746e2e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29923. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Open-vocabulary semantic segmentation (OVSS) relies on vision-language alignment to recognize arbitrary text-defined categories, yet this alignment is fragile under continual test-time distribution shift. Our diagnostic analysis reveals that entropy minimization drives patch-level class collapse, continual updates erode vision-language alignment, and redundant gradients from low-shift samples waste computation. We propose Diversify, Anchor, and Filter (DAF), a stabilization framework that augments entropy-based adaptation with a marginal diversity loss that resists collapse, a cross-modal anchor consistency loss that constrains feature drift relative to a frozen source model, and feature salience filtering that skips low-value backward passes to offset part of the source-anchor overhead. We evaluate on five datasets spanning natural scenes, autonomous driving, underwater imagery, and remote sensing with their corrupted variants. Across the evaluated continual shifts, DAF remains stable where entropy minimization collapses, improving mIoU by over 8 points on Pascal VOC20-C, over 9 points on LoveDA, and over 3 points on Foggy Cityscapes compared to the source model, and is robust to aggressive adaptation and learning rate choices.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.29923 — 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 2026-10-17T08:13:26.922Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).