English

GPF-Net: Gated Progressive Fusion Learning for Polyp Re-Identification

Computer Vision and Pattern Recognition 2025-12-29 v1 Artificial Intelligence

Abstract

Colonoscopic Polyp Re-Identification aims to match the same polyp from a large gallery with images from different views taken using different cameras, which plays an important role in the prevention and treatment of colorectal cancer in computer-aided diagnosis. However, the coarse resolution of high-level features of a specific polyp often leads to inferior results for small objects where detailed information is important. To address this challenge, we propose a novel architecture, named Gated Progressive Fusion network, to selectively fuse features from multiple levels using gates in a fully connected way for polyp ReID. On the basis of it, a gated progressive fusion strategy is introduced to achieve layer-wise refinement of semantic information through multi-level feature interactions. Experiments on standard benchmarks show the benefits of the multimodal setting over state-of-the-art unimodal ReID models, especially when combined with the specialized multimodal fusion strategy.

Keywords

Cite

@article{arxiv.2512.21476,
  title  = {GPF-Net: Gated Progressive Fusion Learning for Polyp Re-Identification},
  author = {Suncheng Xiang and Xiaoyang Wang and Junjie Jiang and Hejia Wang and Dahong Qian},
  journal= {arXiv preprint arXiv:2512.21476},
  year   = {2025}
}

Comments

Work in progress

R2 v1 2026-07-01T08:40:34.868Z