Research map / Detection and segmentation / Open-set and few-shot detection
AcZeroTS: Active Learning for Zero-shot Tissue Segmentation in Pathology Images
Jiao Tang, Junjie Zhou, Bo Qian, Peng Wan, Yingli Zuo, Wei Shao, Daoqiang Zhang
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 |
|---|---|---|---|
| select samples with the combined uncertainty, prototype and contrast query score instead of baseline active learning criteria | AcZeroTS · TNBC (1 unseen), cycle C3 | hIoU: 46.0 -> 52.3 | Improved |
| combined query strategy versus the second-best method on TNBC with 3 unseen classes | AcZeroTS · TNBC (3 unseen), cycle C3 | hIoU: 33.1 -> 37.7 | Improved |
| combined query strategy versus second-best method on HPBC | AcZeroTS · HPBC (1 unseen), cycle C3 | hIoU: 32.8 -> 36.8 | Improved |
| combined query strategy versus second-best method on Pascal VOC | AcZeroTS · Pascal VOC 2012, cycle C4 | hIoU: 73.0 -> 77.1 | Improved |
| use all three query criteria together instead of a single criterion (US, PS or CS alone) (ablation) | AcZeroTS · TNBC and HPBC | hIoU | Improved |
| include the uncertainty score (US) in the query (ablation) | AcZeroTS · TNBC and HPBC | hIoU | Improved |
| include the prototype score (PS) in the query (ablation) | AcZeroTS · TNBC and HPBC | hIoU | Improved |
| include the contrast score (CS) in the query (ablation) | AcZeroTS · TNBC and HPBC | hIoU | Improved |
| use ProZS prototype-guided model with LLM descriptions and pixel contrastive loss instead of TagCLIP | PLIP-based zero-shot segmentation · TNBC (2 unseen) | mIoU(U): 30.1 -> 33.7 | Improved |
| use ProZS instead of TagCLIP on HPBC | PLIP-based zero-shot segmentation · HPBC (1 unseen) | mIoU(U): 32.1 -> 35.1 | Improved |
Closest papers by meaning
- ZePT: Zero-Shot Pan-Tumor Segmentation via Query-Disentangling and Self-Prompting (CVPR 2024 · similarity 0.87)
- Advancing Generalizable Tumor Segmentation with Anomaly-Aware Open-Vocabulary Attention Maps and Frozen Foundation Diffusion Models (CVPR 2025 · similarity 0.86)
- CPLIP: Zero-Shot Learning for Histopathology with Comprehensive Vision-Language Alignment (CVPR 2024 · similarity 0.86)
- Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation (CVPR 2025 · similarity 0.85)
- FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classification (CVPR 2025 · similarity 0.85)
- Semantic and Visual Crop-Guided Diffusion Models for Heterogeneous Tissue Synthesis in Histopathology (NeurIPS 2025 · similarity 0.85)
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.
