YOLOCS: Object Detection based on Dense Channel Compression for Feature Spatial Solidification
This work addresses object detection for computer vision applications, presenting an incremental improvement over YOLOv5.
The paper tackles object detection by proposing YOLOCS, which integrates Dense Channel Compression for Feature Spatial Solidification and an Asymmetric Multi-Level Compression Decoupled Head into YOLOv5, achieving AP improvements of 1.1% to 5.2% on MSCOCO while maintaining similar inference speeds.
In this study, we examine the associations between channel features and convolutional kernels during the processes of feature purification and gradient backpropagation, with a focus on the forward and backward propagation within the network. Consequently, we propose a method called Dense Channel Compression for Feature Spatial Solidification. Drawing upon the central concept of this method, we introduce two innovative modules for backbone and head networks: the Dense Channel Compression for Feature Spatial Solidification Structure (DCFS) and the Asymmetric Multi-Level Compression Decoupled Head (ADH). When integrated into the YOLOv5 model, these two modules demonstrate exceptional performance, resulting in a modified model referred to as YOLOCS. Evaluated on the MSCOCO dataset, the large, medium, and small YOLOCS models yield AP of 50.1%, 47.6%, and 42.5%, respectively. Maintaining inference speeds remarkably similar to those of the YOLOv5 model, the large, medium, and small YOLOCS models surpass the YOLOv5 model's AP by 1.1%, 2.3%, and 5.2%, respectively.