{
  "id": 18794,
  "url": "https://arxiv.org/abs/2608.11681v1",
  "title": "Learning from Multimodal Pseudo-Labels for Robust Open-Vocabulary Instance and Panoptic Segmentation",
  "summary": "This work addresses the challenge of open-vocabulary instance segmentation (OVIS) and open-set panoptic segmentation (OSPS), which aim to recognize both predefined and unseen object categories without exhaustive human annotations. Existing methods often suffer from noisy pseudo-masks, limited visual-textual grounding, and difficulty handling synonyms or out-of-vocabulary (OOV) words. To overcome these challenges, we propose a multimodal framework that leverages pre-trained vision-language models",
  "authors": "Duy Tran Thanh, Yeejin Lee, Byeongkeun Kang",
  "category": "research",
  "topics": null,
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-12T05:39:57.000Z",
  "fetched_at": "2026-08-13T05:10:37.786Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/18794",
  "original_url": "https://arxiv.org/abs/2608.11681v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}