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

计算机视觉-Archer

已于 2023-07-06 16:35:56 修改

阅读量513

点赞数

分类专栏：读论文（SOD-COD-图像分割-Diffusion）文章标签：目标检测人工智能计算机视觉

于 2023-07-06 16:35:46 首次发布

本文链接：https://blog.youkuaiyun.com/zjc910997316/article/details/131579622

版权

读论文（SOD-COD-图像分割-Diffusion）专栏收录该内容

39 篇文章 ¥19.90 ¥99.00

订阅专栏

超级会员免费看

本文提出DGNet，一种利用目标梯度监督的深度框架，用于伪装目标检测。该框架包含上下文和纹理编码器，通过梯度诱导的过渡实现特征软分组。DGNet在性能上超越现有模型，并且其轻量级版本DGNet-S能实时运行，参数效率高。此外，DGNet还在息肉分割、缺陷检测和透明目标分割等领域表现出色。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

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 t

了解本专栏