Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Bi-Directional Cascade Network for Perceptual Edge Detection

About

Exploiting multi-scale representations is critical to improve edge detection for objects at different scales. To extract edges at dramatically different scales, we propose a Bi-Directional Cascade Network (BDCN) structure, where an individual layer is supervised by labeled edges at its specific scale, rather than directly applying the same supervision to all CNN outputs. Furthermore, to enrich multi-scale representations learned by BDCN, we introduce a Scale Enhancement Module (SEM) which utilizes dilated convolution to generate multi-scale features, instead of using deeper CNNs or explicitly fusing multi-scale edge maps. These new approaches encourage the learning of multi-scale representations in different layers and detect edges that are well delineated by their scales. Learning scale dedicated layers also results in compact network with a fraction of parameters. We evaluate our method on three datasets, i.e., BSDS500, NYUDv2, and Multicue, and achieve ODS Fmeasure of 0.828, 1.3% higher than current state-of-the art on BSDS500. The code has been available at https://github.com/pkuCactus/BDCN.

Jianzhong He, Shiliang Zhang, Ming Yang, Yanhu Shan, Tiejun Huang• 2019

Related benchmarks

TaskDatasetResultRank
Boundary DetectionBSDS 500 (test)
ODS82.8
185
Edge DetectionNYUDv2 (test)
ODS Score76.6
93
Edge DetectionBSDS v1 (test)
ODS81.7
32
Edge DetectionBIPED (test)
ODS83.9
31
Boundary DetectionMulticue Boundary
ODS83.8
26
Edge DetectionNYUD Standard Evaluation - SEval v2 (val)
ODS74.8
17
Edge DetectionMulticue Edge
ODS89.4
15
Edge DetectionMulti-Cue
ODS89.1
13
Edge DetectionNYUD Crispness-emphasized evaluation - CEval v2 (val)
ODS Score42.6
13
Boundary DetectionMulti-Cue (test)
ODS0.836
12
Showing 10 of 16 rows

Other info

Code

Follow for update