Semantic Edge Detection with Diverse Deep Supervision.

Liu, Yun; Cheng, Ming-Ming; Fan, Deng-Ping; Zhang, Le; Bian, Jia-Wang; Tao, Dacheng

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.

CONVOLUTIONAL neural networks; EDGES (Geometry); OBJECT recognition (Computer vision)

International Journal of Computer Vision, 2022, Vol 130, Issue 1, p179

0920-5691

Academic Journal

10.1007/s11263-021-01539-8