Research map / Detection and segmentation / CNN features
CerDETR: Cell-Prior Empowered DETR for Cervical Lesion Detection
Linyun Zhou, Jin Chen, Weihan Li, Hengrui Lou, Lingxiang Jia, Weijun Qin, Xiuming Zhang, Zunlei Feng
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 Prior Corrector branch with Cellpose priors and IoU matching (ablation) | DINO · CDetector | AP: 30.9 -> 33.4 | Improved |
| add Auto MPG priors (ablation) | DINO + Prior Corrector · CDetector | AP: 33.4 -> 37.2 | Improved |
| add ICG matching (ablation) | CerDETR · CDetector | AP: 37.2 -> 38.4 | Improved |
| add Prior Query Enhance (label and scale embeddings) (ablation) | CerDETR · CDetector | AP: 38.4 -> 39.1 | Improved |
| replace Auto MPG with plain Cellpose priors (ablation) | CerDETR · CDetector | AP: 39.1 -> 36.7 | Hurt |
| replace Auto MPG with random priors (ablation) | CerDETR · CDetector | AP: 39.1 -> 32.1 | Hurt |
| replace Auto MPG with SAM or CellSAM priors (ablation) | CerDETR · CDetector | AP: 39.1 -> 35.8 (SAM), 34.2 (CellSAM) | Hurt |
| increase prior count n from 300 to 1000 (ablation) | CerDETR · CDetector | AP: 39.1 -> 38.2 | Hurt |
| increase prior count n from 300 to 1000 (ablation) | CerDETR · CDetector | GPU peak usage: 26.6 -> 38.5 | Hurt |
| vary diameter sets and IoU thresholds (ablation) | CerDETR · CDetector | AP: fluctuation about 1.5% AP, 2% AR | No clear effect |
| use CerDETR instead of generic DETR on blood cells | CerDETR · BCCD | AP: 61.3 -> 65.8 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- DEIM — DEIM: DETR with Improved Matching for Fast Convergence (CVPR 2025) · better on 4 of 4 shared results
- Mr. DETR — Mr. DETR: Instructive Multi-Route Training for Detection Transformers (CVPR 2025) · better on 2 of 2 shared results
- Faster R-CNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · better on 2 of 2 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
- Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction (NeurIPS 2026 · similarity 0.83)
- Sequential Attention-based Sampling for Histopathological Analysis (NeurIPS 2025 · similarity 0.83)
- MEATRD: Multimodal Anomalous Tissue Region Detection Enhanced with Spatial Transcriptomics (AAAI 2025 · similarity 0.82)
- EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models (NeurIPS 2026 · similarity 0.82)
- TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor Analysis (ICLR 2026 · similarity 0.82)
- Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology (NeurIPS 2025 · similarity 0.82)
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.
