Semantic Edge Detection with Diverse Deep Supervision

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.

International Journal of Computer Vision

References in corpus (6)

• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Richer Convolutional Features for Edge Detection
• Deeply supervised salient object detection with short connections
• Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
• Three Birds One Stone: A General Architecture for Salient Object Segmentation, Edge Detection and Skeleton Extraction
• Simultaneous Edge Alignment and Learning

Cited by in corpus (13)

• JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds
• Learning Part Boundaries from 3D Point Clouds
• MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation
• Contrast-weighted Dictionary Learning Based Saliency Detection for Remote Sensing Images
• DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection
• SE2Net: Siamese Edge-Enhancement Network for Salient Object Detection
• Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task
• Dynamic Feature Fusion for Semantic Edge Detection
• Panoptic Edge Detection
• CAFENet: Class-Agnostic Few-Shot Edge Detection Network
• DOOBNet: Deep Object Occlusion Boundary Detection from an Image
• Pixel-Pair Occlusion Relationship Map(P2ORM): Formulation, Inference & Application
• ELKPPNet: An Edge-aware Neural Network with Large Kernel Pyramid Pooling for Learning Discriminative Features in Semantic Segmentation