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

TL;DR

This paper introduces GPF-Net, a novel deep learning architecture that enhances polyp re-identification by selectively fusing multi-level features through gated progressive fusion, improving accuracy in medical image matching.

Contribution

The paper proposes a gated progressive fusion network with a new feature fusion strategy for improved polyp re-identification in colonoscopy images.

Findings

Outperforms state-of-the-art unimodal models on benchmark datasets.

Multimodal fusion significantly improves re-identification accuracy.

Layer-wise semantic refinement enhances feature representation.

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.