Metraipolis › archive › dc_d5d8fe901112

GarmentSegAgent: Autonomous Garment Segmentation for Web Fashion Images via Textual Self-Refinement — arXiv:2610.36506

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.36506
License (as archived)
CC0-1.0
Archived
2026-10-28T03:02:05.235Z
SHA-256 of the archived text
a225be4fe9f1edc427fa2b01fa58a2a9ad7f44158599cde460765e2e1c68f8f1
Stable URL of this page
https://metraipolis.com/documento/dc_d5d8fe901112

How to cite

GarmentSegAgent: Autonomous Garment Segmentation for Web Fashion Images via Textual Self-Refinement — arXiv:2610.36506 — arXiv (en), https://arxiv.org/abs/2610.36506 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d5d8fe901112 (Metraipolis archive dc_d5d8fe901112, sha256 a225be4fe9f1edc427fa2b01fa58a2a9ad7f44158599cde460765e2e1c68f8f1)
BibTeX
@misc{dcd5d8fe901112,
  title = {GarmentSegAgent: Autonomous Garment Segmentation for Web Fashion Images via Textual Self-Refinement — arXiv:2610.36506},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.36506},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d5d8fe901112; sha256 a225be4fe9f1edc427fa2b01fa58a2a9ad7f44158599cde460765e2e1c68f8f1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.36506. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Web fashion images support applications such as visual product search and consumer-to-shop matching, yet their visual heterogeneity makes reliable garment segmentation challenging. Despite advances in promptable segmentation, autonomously identifying and correcting garment-specific errors without human-provided spatial prompts remains difficult. We propose GarmentSegAgent, an autonomous framework that integrates semantic planning, spatial execution, and visual evaluation through iterative textual self-refinement. At its core, we introduce CAST (Constrained Attribution-guided Selective TextGrad), which connects visual error attribution with targeted textual optimization. CAST identifies instruction components responsible for segmentation errors, selectively updates them through textual gradients, and validates the resulting instructions against garment-specific constraints. This enables image-specific error correction at inference time while keeping the underlying foundation models frozen. Experiments on DeepFashion2, ModaNet, and Fashionpedia demonstrate consistent improvements in region overlap and boundary accuracy, alongside more reliable refinement than conventional TextGrad. By enabling visual feedback to guide controlled instruction updates, GarmentSegAgent offers a promising direction for autonomous garment understanding, with potential applications in scalable fashion content analysis, visual retrieval, and consumer-to-shop matching on the Web.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.36506 — 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 2026-10-28T03:01:03.533Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).