Papers › A Doubly Decoupled Network for edge detection

A Doubly Decoupled Network for edge detection

1 Apr 2025Neurocomputing 2025 4archive 2025-07-28

Yachuan Li, Xavier Soria Poma, Yongke Xi, Guanlin Li, Chaozhi Yang, Qian Xiao, Yun Bai, Zongmin Li

Deep learning-based edge detectors are increasingly scaled up to achieve higher performance. However, this growth comes at the cost of higher computational demands and a greater risk of model overfitting. In this paper, a Doubly Decoupled Network (DDN) is proposed to alleviate these problems by decoupling the data and features separately. Firstly, we decouple image-edge pairs and build learnable Gaussian distributions. The images are mapped to learnable Gaussian distributions, and the corresponding edges are mapped to samples of the distributions. More robust features are generated by normalizing the latent variables and sampling from the Gaussian distributions. Secondly, we compress the redundant calculations by decoupling image features. Shallow features need not only high resolution to provide accurate spatial information, but also diversity to provide sufficient cues for deep features. We decouple image features into spatial and semantic features and encode them separately. Shallow features no longer provide cues for semantic features and their diversity can be drastically compressed. The proposed DDN achieves the state-of-the-art accuracy across multiple edge detection benchmarks, while the computational cost is similar to that of VGG-based methods. The code is available at https://github.com/Li-yachuan/DDN.

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Results from the paper archive 2025-07-28

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections