arXiv：cs.AI· Suncheng Xiang, Xiaoyang Wang, Junjie Jiang, Hejia Wang, Dahong Qian·· 3 小时前
GPF-Net：用于结肠镜息肉重识别的门控渐进融合学习
GPF-Net: Gated Progressive Fusion Learning for Polyp Re-Identification
AI 导读
针对结肠镜息肉重识别（ReID）中高层特征粒度粗糙、小息肉匹配精度不足的问题，研究者提出多模态特征融合架构 GPF-Net（Gated Progressive Fusion Network），通过全连接门控机制选择性整合多层级特征。
正文
Abstract:Colonoscopic Polyp Re-Identification (ReID) aims to match the same polyp across a large gallery of images captured from different viewpoints and with different cameras, playing a critical role in computer-aided diagnosis for the prevention and treatment of colorectal cancer. However, the coarse granularity of high-level features often limits performance on small polyps, where fine-grained details are essential for accurate matching. To address this challenge, we propose a novel multimodal feature fusion architecture, termed the Gated Progressive Fusion Network, which selectively integrates features from multiple levels through fully connected gating mechanisms. Building on this framework, we introduce a gated progressive fusion strategy that enables layer-wise refinement of semantic information, facilitating multi-level feature interactions to enhance both generalization ability and robustness. Extensive experiments on standard benchmarks demonstrate the advantages of the multimodal setting over state-of-the-art unimodal ReID models, particularly when combined with the proposed fusion strategy tailored for general-purpose scenarios.
| Comments: | Accepted by BIBM2026 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2512.21476 [cs.CV] |
| (or arXiv:2512.21476v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2512.21476 arXiv-issued DOI via DataCite |
Submission history
From: Suncheng Xiang [view email]
[v1]
Thu, 25 Dec 2025 02:40:46 UTC (2,524 KB)
[v2]
Thu, 8 Oct 2026 09:21:10 UTC (2,495 KB)
来源：arXiv：cs.AI · arxiv.org