{
  "id": 7068,
  "url": "https://arxiv.org/abs/2603.17655v2",
  "title": "Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment",
  "summary": "Cross-Domain Few-Shot Learning (CDFSL) adapts models trained with large-scale general data (source domain) to downstream target domains with only scarce training data, where the research on vision-language models (e.g., CLIP) is still in the early stages. Typical downstream domains, such as medical diagnosis, require fine-grained visual cues for interpretable recognition, but we find that current fine-tuned CLIP models can hardly focus on these cues, albeit they can roughly focus on important re",
  "authors": "Yaze Zhao, Yixiong Zou, Yuhua Li, Ruixuan Li",
  "category": "research",
  "topics": "safety-alignment,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-18T12:20:21.000Z",
  "fetched_at": "2026-07-14T16:32:59.162Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/7068",
  "original_url": "https://arxiv.org/abs/2603.17655v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}