Bi-Directional Cascade Network for Perceptual Edge Detection

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

353 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Xiaogang Wang
3. Ming-Hsuan Yang
4. Qi Tian
5. Dacheng Tao
6. Yi Yang
7. Alan L. Yuille
8. Haibin Ling

Citations in the corpus

• EDTER: Edge Detection with Transformer (2022, methodology): “(a) Input (b) Ground truth (c) RCF [36] (d) CED [62] (e) BDCN [22] (f) EDTER (Ours)”
• Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection (2019, methodology): “As can Image GT CED [34] HED [36] RCF [20] BDCN [14] DexiNed be appreciated from Table 1(b), DexiNed-a reaches the best results in all evaluation metrics.”
• Pixel Difference Networks for Efficient Edge Detection (2021, methodology): “Furthermore, PiDiNet can be trained BDCNCEDRCF PiDiNetImage GT Figure 9.”
• A Survey of Deep Learning-Based Object Detection (2019, background): “[263] propose a Bi-Directional Cascade Network to let one layer supervised by labeled edges while adopt dilated”
• RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth (2021, background): “As shown in Table 1, ten compared models are symbolized as HED, RCF, CED, DexiNed, BDCN, CASENet, DFF, *DeepLabV3+, *DOOBNet and *OFNet, respectively.”
• Deepstrip: High-Resolution Boundary Refinement (2020, background): “Recent decades have witnessed considerable effort to improve the boundary quality of an object that has been detected [41, 35, 32, 18, 37, 47, 16, 22] or segmented [11, 34, 24, 7].”