Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Deep Gradient Learning for Efficient Camouflaged Object Detection

About

This paper introduces 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 (80 fps) and achieves comparable results to the cutting-edge model JCSOD-CVPR$_{21}$ with only 6.82% parameters. Application results also show that the proposed DGNet performs well in polyp segmentation, defect detection, and transparent object segmentation tasks. Codes will be made available at https://github.com/GewelsJI/DGNet.

Ge-Peng Ji, Deng-Ping Fan, Yu-Cheng Chou, Dengxin Dai, Alexander Liniger, Luc Van Gool• 2022

Related benchmarks

TaskDatasetResultRank
Camouflaged Object DetectionCOD10K (test)
S-measure (S_alpha)0.844
306
Camouflaged Object DetectionCOD10K
S-measure (S_alpha)0.822
217
Camouflaged Object DetectionCAMO (test)
M0.051
154
Camouflaged Object DetectionNC4K
MAE0.042
72
Camouflaged Object SegmentationCAMO (test)
S-measure (S_alpha)0.839
56
Camouflaged Object SegmentationNC4K
Fw_beta78.4
41
Camouflaged Object DetectionNC4K
S_alpha0.875
33
Referring Camouflaged Object DetectionR2C7K
Sm82.1
32
Camouflaged Object DetectionWeeds-Banana (test)
S_alpha0.8439
23
Camouflaged Object DetectionCAMO
MAE5.7
22
Showing 10 of 12 rows

Other info

Follow for update