Research map / Detection and segmentation / CNN features
WeaveSeg: Iterative Contrast-weaving and Spectral Feature-refining for Nuclei Instance Segmentation
Jiajia Li, Huisi Wu, Jing Qin
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 |
|---|---|---|---|
| add ICW module (ablation) | WeaveSeg without ICW · CoNSeP | Dice: 0.835 -> 0.852 | Improved |
| add ASR module (ablation) | WeaveSeg without ASR · CoNSeP | Dice: 0.844 -> 0.852 | Improved |
| add ICW module (ablation) | WeaveSeg without ICW · CoNSeP | AJI: 0.529 -> 0.563 | Improved |
| add ASR module (ablation) | WeaveSeg without ASR · CoNSeP | AJI: 0.547 -> 0.563 | Improved |
| add both ASR and ICW (ablation) | U-Net baseline · CoNSeP | HausD: 27.381 -> 25.835 | Improved |
| add foreground/background losses Lfg and Lbg (ablation) | WeaveSeg ICW (no ASR) · MoNuSeg | AJI: 0.588 -> 0.603 | Improved |
| add trilateral loss Ltri (ablation) | WeaveSeg ICW (no ASR) · MoNuSeg | AJI: 0.603 -> 0.624 | Improved |
| add uncertainty loss Luncert (ablation) | WeaveSeg ICW (no ASR) · MoNuSeg | AJI: 0.624 -> 0.644 | Improved |
| add uncertainty loss Luncert (ablation) | WeaveSeg ICW (no ASR) · MoNuSeg | F1: 0.877 -> 0.874 | Hurt |
| add uncertainty loss Luncert (ablation) | WeaveSeg ICW (no ASR) · CoNSeP | AJI: 0.542 -> 0.547 | Improved |
| use 3 ICW iterations instead of none (ablation) | WeaveSeg · MoNuSeg | AJI: 0.582 -> 0.648 | Improved |
| increase ICW iterations from 3 to 4 (ablation) | WeaveSeg · MoNuSeg | AJI: 0.648 -> 0.635 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Mudslide — Mudslide: A Universal Nuclear Instance Segmentation Method (CVPR 2024) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CiNuSeg: Class Incremental Nuclei Segmentation via Anchor-driven Consistency Learning with Dual Region Regularization (AAAI 2026 · similarity 0.87)
- TopoSeg: Topology-Aware Nuclear Instance Segmentation (ICCV 2023 · similarity 0.86)
- Bridging RGB and Hematoxylin Components: An Interleaved Guidance and Fusion Framework for Point Supervised Nuclei Segmentation (CVPR 2026 · similarity 0.85)
- Incremental Nuclei Segmentation from Histopathological Images via Future-class Awareness and Compatibility-inspired Distillation (CVPR 2024 · similarity 0.85)
- $\epsilon$-Seg: Sparsely Supervised Semantic Segmentation of Microscopy Data (NeurIPS 2025 · similarity 0.83)
- Are nuclear masks all you need for improved out-of-domain generalisation? A closer look at cancer classification in histopathology (NeurIPS 2024 · similarity 0.83)
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.
