[读论文]---[高效COD] DGNet:Deep Gradient Learning for Efficient CamouflagedObject Detection

This paper introduces deep gradient network (DGNet), a novel deep framework that exploits object gradient supervision for camouflaged object detection (COD).  
It decouples the task into two connected branches, i.e., a context and a texture encoder.  
The essential connection is the gradient-induced transition, representing a soft grouping between context and texture features.   Benefiting from the simple but efficient framework, DGNet outperforms existing state-of-the-art COD models by a large margin.   Notably, our efficient version, DGNet-S, runs in real-time (80fps) and achieves comparable results to the cutting-edge model JCSOD-CVPR21 with only 6.82% parameters.   The application results also show that the proposed DGNet performs well in the polyp segmentation, defect detection, and transparent object segmentation tasks.   The code will be made available at

本文介绍了一种利用目标梯度监督进行伪装目标