Research map / Vision-language and multimodal / CLIP and zero-shot
Quilt-1M: One Million Image-Text Pairs for Histopathology
Wisdom Oluchi Ikezogwo, Mehmet Saygin Seyfioglu, Fatemeh Ghezloo, Dylan Stefan Chan Geva, Fatwir Sheikh Mohammed, Pavan Kumar Anand, Ranjay Krishna, Linda Shapiro
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| fine-tune CLIP ViT-B/32 on QUILT-1M (QuiltNet) instead of using PLIP (trained on OpenPath) | CLIP ViT-B/32 · SICAPv2 linear probe 100% | accuracy %: 73.0 -> 75.48 | Improved |
| fine-tune CLIP ViT-B/32 on QUILT-1M instead of using PLIP | CLIP ViT-B/32 · SkinCancer linear probe 100% | accuracy %: 93.29 -> 93.03 | No clear effect |
| fine-tune CLIP on QUILT-1M (ViT-B/32) vs off-the-shelf CLIP | CLIP ViT-B/32 · NCT-CRC linear probe 100% | accuracy %: 91.83 -> 95.22 | Improved |
| QUILT-1M-tuned model vs BiomedCLIP (PubMedBERT text encoder) | ViT-B/16 PMB/256 · QUILT-1M holdout text-to-image R@50 | R@50 %: 14.99 -> 30.28 | Improved |
| QUILT-1M-tuned model vs BiomedCLIP on ARCH | ViT-B/16 PMB/256 · ARCH text-to-image R@50 | R@50 %: 53.24 -> 55.14 | Improved |
| train CLIP from scratch instead of fine-tuning pre-trained CLIP on QUILT-1M (ablation) | QuiltNet · downstream histopathology tasks | performance | Hurt |
| use 10% balanced subset instead of 100% training data for linear probe | linear probe · imbalanced datasets | accuracy % | Mixed |
Closest papers by meaning
- Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos (CVPR 2024 · similarity 0.92)
- STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomics (NeurIPS 2024 · similarity 0.88)
- PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration (ICLR 2025 · similarity 0.87)
- THUNDER: Tile-level Histopathology image UNDERstanding benchmark (NeurIPS 2025 · similarity 0.87)
- CPLIP: Zero-Shot Learning for Histopathology with Comprehensive Vision-Language Alignment (CVPR 2024 · similarity 0.87)
- Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
