{
  "id": 12956,
  "url": "https://arxiv.org/abs/2607.20326v1",
  "title": "Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout",
  "summary": "RGB-D semantic segmentation has achieved remarkable progress, yet most models assume that RGB and depth are always available. In practice, failures or occlusions of surveillance sensors often remove one modality. Although RGB or depth alone can contain sufficient cues, models trained only on full-modality inputs fail to exploit the remaining modality once one is missing, causing severe degradation. We tackle this issue with a simple continued-training paradigm, \\emph{Condition Dropout (ConD)}, w",
  "authors": "Xuchen Zhu, Yajuan Wei, Shuang Hao, Jiwei Jiang, Guanxiang Mao, Fang Ren",
  "category": "research",
  "topics": "privacy-surveillance",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-22T16:12:27.000Z",
  "fetched_at": "2026-07-23T05:10:49.458Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/12956",
  "original_url": "https://arxiv.org/abs/2607.20326v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}