Research map / Detection and segmentation / CNN features
SFCN-OPI: Detection and Fine-Grained Classification of Nuclei Using Sibling FCN With Objectness Prior Interaction
Yanning Zhou, Qi Dou, Hao Chen, Jing Qin, Pheng-Ann Heng
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 |
|---|---|---|---|
| replace one five-class FCN with sibling detection and classification branches sharing early features (ablation) | FCN-5CLS · Colorectal nuclei dataset | Classification F1: 0.298 to 0.496 | Improved |
| replace one five-class FCN with sibling detection and classification branches sharing early features (ablation) | FCN-5CLS · Colorectal nuclei dataset | Detection F1: 0.790 to 0.807 | Improved |
| add objectness prior interaction and dynamically gate classification loss using high-objectness locations (ablation) | SFCN · Colorectal nuclei dataset | Classification F1: 0.496 to 0.742 | Improved |
| add objectness prior interaction and dynamically gate classification loss using high-objectness locations (ablation) | SFCN · Colorectal nuclei dataset | Detection F1: 0.807 to 0.834 | Improved |
| add joint training after detection-branch pre-training (ablation) | SFCN-OPI-1 · Colorectal nuclei dataset | Classification F1: 0.613 to 0.711 | Improved |
| add a separate classification pre-training step before joint training (ablation) | SFCN-OPI-2 · Colorectal nuclei dataset | Classification F1: 0.711 to 0.742 | Improved |
| use SFCN-OPI instead of SC-CNN | SC-CNN · Colorectal nuclei dataset | Classification F1: 0.692 to 0.742 | Improved |
Closest papers by meaning
- Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection (ICCV 2023 · similarity 0.87)
- Are nuclear masks all you need for improved out-of-domain generalisation? A closer look at cancer classification in histopathology (NeurIPS 2024 · similarity 0.86)
- Cell Graph Transformer for Nuclei Classification (AAAI 2024 · similarity 0.86)
- Incremental Nuclei Segmentation from Histopathological Images via Future-class Awareness and Compatibility-inspired Distillation (CVPR 2024 · similarity 0.85)
- UniCell: Universal Cell Nucleus Classification via Prompt Learning (AAAI 2024 · similarity 0.85)
- STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology (NeurIPS 2025 · similarity 0.84)
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.
