Metraipolis › archive › dc_7e8a588a97b6

Vision-Language-Guided Pseudo-Labels for Unsupervised Domain Adaptation in Semantic Segmentation for Waste Sorting — arXiv:2609.00898

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00898
License (as archived)
CC0-1.0
Archived
2026-10-17T06:33:44.653Z
SHA-256 of the archived text
8c2ea1d893dc276284e76090be64386827d79a3ed45d81d41d44b77a53631c7a
Stable URL of this page
https://metraipolis.com/documento/dc_7e8a588a97b6

How to cite

Vision-Language-Guided Pseudo-Labels for Unsupervised Domain Adaptation in Semantic Segmentation for Waste Sorting — arXiv:2609.00898 — arXiv (en), https://arxiv.org/abs/2609.00898 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e8a588a97b6 (Metraipolis archive dc_7e8a588a97b6, sha256 8c2ea1d893dc276284e76090be64386827d79a3ed45d81d41d44b77a53631c7a)
BibTeX
@misc{dc7e8a588a97b6,
  title = {Vision-Language-Guided Pseudo-Labels for Unsupervised Domain Adaptation in Semantic Segmentation for Waste Sorting — arXiv:2609.00898},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00898},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e8a588a97b6; sha256 8c2ea1d893dc276284e76090be64386827d79a3ed45d81d41d44b77a53631c7a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00898. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Obtaining labeled data for semantic segmentation in applied settings (e.g., autonomous driving, industrial waste sorting) is expensive and often infeasible at scale. We present a cross-modal pseudo-labeling pipeline that enables unsupervised domain adaptation without any target-domain annotations. The pipeline is built on two core foundation models: SAM generates class-agnostic region proposals, and EVA-CLIP assigns semantic labels based on region-text similarity, with confidence filtering ensuring that only reliable pseudo-labels are used for self-training a segmentation model. As an optional extension, BLIP provides language-grounded verification for ambiguous regions, thereby improving pseudo-label quality without altering the overall pipeline. Evaluated on two domain shifts, synthetic-to-real autonomous driving and, with a primary focus, lab-to-factory industrial waste sorting, the pipeline consistently improves over source-only baselines. Our results demonstrate that pseudo-label quality, not quantity, is a decisive factor in self-training under domain shift, and that cross-modal language grounding offers a practical path to reliable automatic annotation in deployment-critical applications.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.00898 — 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 2026-10-17T06:15:12.834Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).