English

Semantic Edge Detection with Diverse Deep Supervision

Computer Vision and Pattern Recognition 2021-10-28 v5

Abstract

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 (DDS) 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.

Keywords

Cite

@article{arxiv.1804.02864,
  title  = {Semantic Edge Detection with Diverse Deep Supervision},
  author = {Yun Liu and Ming-Ming Cheng and Deng-Ping Fan and Le Zhang and JiaWang Bian and Dacheng Tao},
  journal= {arXiv preprint arXiv:1804.02864},
  year   = {2021}
}

Comments

International Journal of Computer Vision

R2 v1 2026-06-23T01:17:40.017Z