CASIA OpenIR  > 学术期刊  > Machine Intelligence Research
Deep Gradient Learning for Efficient Camouflaged Object Detection
Ge-Peng Ji1
Source PublicationMachine Intelligence Research
AbstractThis 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
KeywordCamouflaged object detection (COD) object gradient soft grouping efficient model image segmentation
Citation statistics
Document Type期刊论文
Collection学术期刊_Machine Intelligence Research
Affiliation1.School of Computer Science, Wuhan University, Wuhan 430072, China
2.Computer Vision Laboratory, ETH Zürich, Zürich 8092, Switzerland
Recommended Citation
GB/T 7714
Ge-Peng Ji. Deep Gradient Learning for Efficient Camouflaged Object Detection[J]. Machine Intelligence Research,2023,20(1):92-108.
APA Ge-Peng Ji.(2023).Deep Gradient Learning for Efficient Camouflaged Object Detection.Machine Intelligence Research,20(1),92-108.
MLA Ge-Peng Ji."Deep Gradient Learning for Efficient Camouflaged Object Detection".Machine Intelligence Research 20.1(2023):92-108.
Files in This Item:
File Name/Size DocType Version Access License
MIR-2022-05-171.pdf(5723KB)期刊论文出版稿开放获取CC BY-NC-SAView
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Ge-Peng Ji]'s Articles
Baidu academic
Similar articles in Baidu academic
[Ge-Peng Ji]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Ge-Peng Ji]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: MIR-2022-05-171.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.