CSDN: A Context-Gated Self-Adaptive Detection Network for Real-Time Object Detection

TL;DR

CSDN introduces a Transformer-based detection head that enhances global context modeling and adapts to objects of various sizes, significantly improving real-time object detection accuracy with minimal fine-tuning.

Contribution

The paper proposes CSDN, a novel context-gated, scale-adaptive detection network inspired by human perception, addressing CNN limitations and redundancy in self-attention modules.

Findings

CSDN improves detection accuracy across multiple CNN-based detectors.

The method enhances global context understanding and scale adaptation.

Minimal fine-tuning yields significant performance gains.

Abstract

Convolutional neural networks (CNNs) have long been the cornerstone of target detection, but they are often limited by limited receptive fields, which hinders their ability to capture global contextual information. We re-examined the DETR-inspired detection head and found substantial redundancy in its self-attention module. To solve these problems, we introduced the Context-Gated Scale-Adaptive Detection Network (CSDN), a Transformer-based detection header inspired by human visual perception: when observing an object, we always concentrate on one site, perceive the surrounding environment, and glance around the object. This mechanism enables each region of interest (ROI) to adaptively select and combine feature dimensions and scale information from different patterns. CSDN provides more powerful global context modeling capabilities and can better adapt to objects of different sizes and structures. Our proposed detection head can directly replace the native heads of various CNN-based detectors, and only a few rounds of fine-tuning on the pre-trained weights can significantly improve the detection accuracy.