Deep Structural Contour Detection

By Ruoxi Deng, Shengjun Liu. 2020

86 citations recorded by the source corpus.

Object contour detection is the fundamental and preprocessing step for multimedia applications such as icon generation, object segmentation, and tracking. The quality of contour prediction is of great importance in these applications since it affects the subsequent process. In this work, we aim to develop a high-performance contour detection system. We first propose a novel yet very effective loss function for contour detection. The proposed loss function is capable of penalizing the distance of contour-structure similarity between each pair of prediction and ground-truth. Moreover, to better distinguishing object contours and background textures, we introduce a novel convolutional encoder-decoder network. Within the network, we present a hyper module that captures dense connections among high-level features and produces effective semantic information. Then the information is progressively propagated and fused with low-level features. We conduct extensive experiments on the BSDS500 and Multi-Cue datasets, the results show significant improvement against the state-of-the-art competitors. We further demonstrate the benefit of our DSCD method for crowd counting.

Subfields: Computer Vision and Pattern Recognition, Media Technology

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. Jingkuan Song
2. Lianli Gao
3. Yaping Huang
4. Haibin Ling
5. Yuming Liu
6. Ji Zhang
7. Cheng Chen
8. Qingji Guan

In Media Technology

1. Yaping Huang
2. Haibin Ling
3. Jingkuan Song
4. Lianli Gao
5. Qingji Guan
6. Mengyang Pu

Citations in the corpus

• EDTER: Edge Detection with Transformer (2022, methodology): “ICCV’15 .851 (0.014) .864 (0.011) - RCF [36] CVPR’17 .857 (0.004) .862 (0.004) - BDCN [22] CVPR’19 .891 (0.001) .898 (0.002) .935(0.002) DSCD [11] ACMMM’20 .871 (0.007) .876 (0.002) - PiDiNet [53] ICCV’21 .855 (0.007) .860 (0.005) - EDTER (Ours) - .894 (0.005) .900 (0.003) .944 (0.002)”
• Class Gradient Projection For Continual Learning (2022, background): “Although the modern deep learning network (DNN) has shown good performance on the task at hand [5, 12, 24, 41, 46, 47], they always violently forget the previous knowledge when they learn new tasks.”
• RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth (2021, background): “CNN-based edge detectors [3, 4, 9, 10, 17, 20, 24, 26, 31, 36, 45] do not rely on hand-crafted features and achieve better performance.”