English

ECC-PolypDet: Enhanced CenterNet with Contrastive Learning for Automatic Polyp Detection

Computer Vision and Pattern Recognition 2024-01-11 v1

Abstract

Accurate polyp detection is critical for early colorectal cancer diagnosis. Although remarkable progress has been achieved in recent years, the complex colon environment and concealed polyps with unclear boundaries still pose severe challenges in this area. Existing methods either involve computationally expensive context aggregation or lack prior modeling of polyps, resulting in poor performance in challenging cases. In this paper, we propose the Enhanced CenterNet with Contrastive Learning (ECC-PolypDet), a two-stage training \& end-to-end inference framework that leverages images and bounding box annotations to train a general model and fine-tune it based on the inference score to obtain a final robust model. Specifically, we conduct Box-assisted Contrastive Learning (BCL) during training to minimize the intra-class difference and maximize the inter-class difference between foreground polyps and backgrounds, enabling our model to capture concealed polyps. Moreover, to enhance the recognition of small polyps, we design the Semantic Flow-guided Feature Pyramid Network (SFFPN) to aggregate multi-scale features and the Heatmap Propagation (HP) module to boost the model's attention on polyp targets. In the fine-tuning stage, we introduce the IoU-guided Sample Re-weighting (ISR) mechanism to prioritize hard samples by adaptively adjusting the loss weight for each sample during fine-tuning. Extensive experiments on six large-scale colonoscopy datasets demonstrate the superiority of our model compared with previous state-of-the-art detectors.

Keywords

Cite

@article{arxiv.2401.04961,
  title  = {ECC-PolypDet: Enhanced CenterNet with Contrastive Learning for Automatic Polyp Detection},
  author = {Yuncheng Jiang and Zixun Zhang and Yiwen Hu and Guanbin Li and Xiang Wan and Song Wu and Shuguang Cui and Silin Huang and Zhen Li},
  journal= {arXiv preprint arXiv:2401.04961},
  year   = {2024}
}

Comments

codes available at https://github.com/yuncheng97/ECC-PolypDet/tree/main

R2 v1 2026-06-28T14:12:56.547Z