AVPDN: Learning Motion-Robust and Scale-Adaptive Representations for Video-Based Polyp Detection

TL;DR

This paper introduces AVPDN, a novel deep learning framework that enhances video-based polyp detection in colonoscopy videos by addressing motion and scale variations through specialized modules, leading to improved accuracy and robustness.

Contribution

The paper presents AVPDN, a new network with adaptive feature interaction and scale-aware modules specifically designed for robust polyp detection in challenging colonoscopy videos.

Findings

Achieves state-of-the-art performance on public benchmarks.

Demonstrates strong generalization across different datasets.

Effectively handles rapid camera movements and multi-scale features.

Abstract

Accurate detection of polyps is of critical importance for the early and intermediate stages of colorectal cancer diagnosis. Compared to static images, dynamic colonoscopy videos provide more comprehensive visual information, which can facilitate the development of effective treatment plans. However, unlike fixed-camera recordings, colonoscopy videos often exhibit rapid camera movement, introducing substantial background noise that disrupts the structural integrity of the scene and increases the risk of false positives. To address these challenges, we propose the Adaptive Video Polyp Detection Network (AVPDN), a robust framework for multi-scale polyp detection in colonoscopy videos. AVPDN incorporates two key components: the Adaptive Feature Interaction and Augmentation (AFIA) module and the Scale-Aware Context Integration (SACI) module. The AFIA module adopts a triple-branch architecture to enhance feature representation. It employs dense self-attention for global context modeling, sparse self-attention to mitigate the influence of low query-key similarity in feature aggregation, and channel shuffle operations to facilitate inter-branch information exchange. In parallel, the SACI module is designed to strengthen multi-scale feature integration. It utilizes dilated convolutions with varying receptive fields to capture contextual information at multiple spatial scales, thereby improving the model's denoising capability. Experiments conducted on several challenging public benchmarks demonstrate the effectiveness and generalization ability of the proposed method, achieving competitive performance in video-based polyp detection tasks.