AINewsnow

New paper extends 2D CLIP-based cell microscopy anomaly detection to 3D morphology with text contrastive learning

A new arXiv paper presents 3D cell morphology–clinical text contrastive learning using a Voxel Swin Transformer and finding-encoder domain adaptation, building on prior 2D CLIP dual-encoder work with LoRA that reached anomaly-scoring ROC-AUC up to 0.985.

Read the full story at arXiv cs.CV ↗

Timeline · 1 report

  1. 2026-11-17 05:00 · arXiv cs.CV
    3D Cell Morphology--Clinical Text Contrastive Learning with Voxel Swin Transformer and Finding Encoder Domain-Adaptation

More stories

  1. DEFTS Offers Data-Efficient, Training-Free Few-Shot Learning for CLIP in Text Subspace — arXiv stat.ML
  2. OpenAI launches GPT-6.2 Astra and Sol as Google ships Gemini 4 Neon and Microsoft unveils MAI Code 2 — OpenAI News
  3. Anthropic debuts on Nasdaq after record $81.3 billion IPO — Anthropic (X)
  4. Google launches Gemini 4 Neon and opens Genie 4 world model to Gemini API developers — Google DeepMind YouTube
  5. Google books Blue Origin's New Glenn for 2029 launch of AI server satellites — Google: The Keyword
  6. AWS expands SageMaker AI with data preparation tools and cross-Region inference routing — AWS Machine Learning Blog
  7. Anthropic's stock debut soars, but Wall Street indexes drop — Washington Post AI
  8. AWS expands SageMaker JumpStart with OpenTSLM, model leaderboard, and PolyAI Dialog-RSN-1 — AWS Machine Learning Blog

Read the Daily Brief: the day's most important AI stories →