Colo-ReID: Discriminative Representation Embedding with Meta-learning for Colonoscopic Polyp Re-Identification

TL;DR

This paper introduces Colo-ReID, a meta-learning based training method for colonoscopic polyp re-identification that improves discriminative feature learning and outperforms existing methods on the task.

Contribution

It proposes a novel meta-learning training framework with a dynamic regulation mechanism specifically designed for colonoscopic polyp re-identification.

Findings

Outperforms second-best method by +2.3% mAP on polyp re-identification

Effective in scenarios with fewer samples

Enhances discriminative feature learning in medical image retrieval

Abstract

Colonoscopic Polyp Re-Identification aims to match the same polyp from a large gallery with images from different views taken using different cameras and plays an important role in the prevention and treatment of colorectal cancer. However, traditional methods for object ReID directly adopting CNN models trained on the ImageNet dataset usually produce unsatisfactory retrieval performance on colonoscopic datasets due to the large domain gap. Additionally, these methods neglect to explore the potential of self-discrepancy among intra-class or inter-class relations in the colonoscopic polyp dataset, which remains an open research problem in the medical community. To solve this dilemma, we propose a simple but effective training method named Colo-ReID, which can help our model learn more general and discriminative knowledge based on the meta-learning strategy in scenarios with fewer samples. Based on this, a dynamic Meta-Learning Regulation mechanism called MLR is introduced to further boost the performance of polyp re-identification. Our experimental results show that Colo-ReID consistently outperforms second-best method in terms of mAP performance by +2.3% on polyp re-identification task. Our source code is also publicly available at https://github.com/JeremyXSC/Colo-ReID.