Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.02090 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910097574199296 |
|---|---|
| author | Kong, Yan Yin, Yuan Chen, Hongan Fang, Yuqi Shan, Caifeng |
| author_facet | Kong, Yan Yin, Yuan Chen, Hongan Fang, Yuqi Shan, Caifeng |
| contents | Automated analysis of Pap smear images is critical for cervical cancer screening but remains challenging due to dense cell distribution and complex morphology. In this paper, we present our winning solution for the RIVA Cervical Cytology Challenge, achieving 1st place in Track B and 2nd place in Track A. Our approach leverages a powerful baseline, integrating the Co-DINO framework with a Swin-Large backbone for robust multi-scale feature extraction. To address the dataset's unique fixed-size bounding box annotations, we formulate the detection task as a center-point prediction problem. Tailoring our approach to this formulation, we introduce a center-preserving data augmentation strategy and an analytical geometric box optimization to effectively absorb localization jitter. Finally, we apply track-specific loss tuning to adapt the loss weights for each task. Experiments demonstrate that our targeted optimizations improve detection performance, providing an effective pipeline for cytology image analysis. Our code is available at https://github.com/YanKong0408/Center-DETR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02090 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Center-Aware Detection with Swin-based Co-DETR Framework for Cervical Cytology Kong, Yan Yin, Yuan Chen, Hongan Fang, Yuqi Shan, Caifeng Computer Vision and Pattern Recognition Automated analysis of Pap smear images is critical for cervical cancer screening but remains challenging due to dense cell distribution and complex morphology. In this paper, we present our winning solution for the RIVA Cervical Cytology Challenge, achieving 1st place in Track B and 2nd place in Track A. Our approach leverages a powerful baseline, integrating the Co-DINO framework with a Swin-Large backbone for robust multi-scale feature extraction. To address the dataset's unique fixed-size bounding box annotations, we formulate the detection task as a center-point prediction problem. Tailoring our approach to this formulation, we introduce a center-preserving data augmentation strategy and an analytical geometric box optimization to effectively absorb localization jitter. Finally, we apply track-specific loss tuning to adapt the loss weights for each task. Experiments demonstrate that our targeted optimizations improve detection performance, providing an effective pipeline for cytology image analysis. Our code is available at https://github.com/YanKong0408/Center-DETR. |
| title | Center-Aware Detection with Swin-based Co-DETR Framework for Cervical Cytology |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.02090 |