Center-Aware Detection with Swin-based Co-DETR Framework for Cervical Cytology

TL;DR

This paper introduces a novel center-aware detection framework for cervical cytology images, achieving top results in a challenge by combining a Swin backbone with specialized data augmentation and loss tuning.

Contribution

The work presents a new detection approach tailored for cytology images, integrating center-point prediction, geometric box optimization, and track-specific loss tuning.

Findings

Achieved 1st place in Track B and 2nd in Track A of the RIVA Cervical Cytology Challenge.

Enhanced detection accuracy through center-preserving data augmentation and geometric box optimization.

Demonstrated effectiveness of the proposed pipeline in cytology image analysis.

Abstract

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.