CSDN: A Context-Gated Self-Adaptive Detection Network for Real-Time Object Detection
This work addresses object detection for computer vision applications, presenting an incremental improvement by enhancing existing CNN-based detectors with a novel head.
The paper tackled the problem of limited receptive fields and redundancy in self-attention modules in object detection by introducing CSDN, a Transformer-based detection head that adaptively selects features and scales, resulting in improved detection accuracy with minimal fine-tuning.
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.