Semantic Edge Detection with Diverse Deep Supervision

By Yun Liu, Ming-Ming Cheng, Jiawang Bian, Le Zhang, Peng-Tao Jiang, Yang Cao. 2018

112 citations recorded by the source corpus.

Semantic edge detection (SED), which aims at jointly extracting edges as well as their category information, has far-reaching applications in domains such as semantic segmentation, object proposal generation, and object recognition. SED naturally requires achieving two distinct supervision targets: locating fine detailed edges and identifying high-level semantics. Our motivation comes from the hypothesis that such distinct targets prevent state-of-the-art SED methods from effectively using deep supervision to improve results. To this end, we propose a novel fully convolutional neural network using diverse deep supervision within a multi-task framework where bottom layers aim at generating category-agnostic edges, while top layers are responsible for the detection of category-aware semantic edges. To overcome the hypothesized supervision challenge, a novel information converter unit is introduced, whose effectiveness has been extensively evaluated on SBD and Cityscapes datasets.

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

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. Ling Shao
2. Deng-Ping Fan
3. Ming-Ming Cheng
4. Jianbing Shen
5. Ge-Peng Ji
6. Wenguan Wang
7. Luc Van Gool
8. Huchuan Lu

In Representation & Self-Supervised Learning

1. Ling Shao
2. Jianbing Shen
3. Guolei Sun
4. Luc Van Gool
5. Ming-Ming Cheng

Citations in the corpus

• Concealed Object Detection (2021, background): “tasks, such as object proposal, localization, semantic edge detection [24], transfer learning [25], domain adaption [26], etc.”
• Camouflaged Object Detection (2020, background): “• All the camouflaged images are hierarchically annotated with category, bounding-box, object-level, and instance-level labels, facilitating many vision tasks, such as localization, object proposal, semantic edge detection [42], task transfer learning [69], etc.”
• Transformer in Convolutional Neural Networks (2021, background): “In the last decade, convolutional neural networks (CNN) have been the go-to architecture in computer vision, owing to their powerful capability in learning representations from images/videos [1–11].”