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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiang, Suncheng, Wang, Xiaoyang, Jiang, Junjie, Wang, Hejia, Qian, Dahong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915694061289472
author Xiang, Suncheng
Wang, Xiaoyang
Jiang, Junjie
Wang, Hejia
Qian, Dahong
author_facet Xiang, Suncheng
Wang, Xiaoyang
Jiang, Junjie
Wang, Hejia
Qian, Dahong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_21476
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GPF-Net: Gated Progressive Fusion Learning for Polyp Re-Identification
Xiang, Suncheng
Wang, Xiaoyang
Jiang, Junjie
Wang, Hejia
Qian, Dahong
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title GPF-Net: Gated Progressive Fusion Learning for Polyp Re-Identification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.21476