CASENet: Deep Category-Aware Semantic Edge Detection

Abstract

Boundary and edge cues are highly beneficial in improving a wide variety of vision tasks such as semantic segmentation, object recognition, stereo, and object proposal generation. Recently, the problem of edge detection has been revisited and significant progress has been made with deep learning. While classical edge detection is a challenging binary problem in itself, the category-aware semantic edge detection by nature is an even more challenging multi-label problem. We model the problem such that each edge pixel can be associated with more than one class as they appear in contours or junctions belonging to two or more semantic classes. To this end, we propose a novel end-to-end deep semantic edge learning architecture based on ResNet and a new skip-layer architecture where category-wise edge activations at the top convolution layer share and are fused with the same set of bottom layer features. We then propose a multi-label loss function to supervise the fused activations. We show that our proposed architecture benefits this problem with better performance, and we outperform the current state-of-the-art semantic edge detection methods by a large margin on standard data sets such as SBD and Cityscapes.

Accepted to CVPR 2017

References in corpus (10)

• Deep Residual Learning for Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Fully Convolutional Networks for Semantic Segmentation
• Convolutional Oriented Boundaries
• Pixel-wise Deep Learning for Contour Detection
• Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
• Layered Interpretation of Street View Images
• Weakly Supervised Object Boundaries

Cited by in corpus (6)

• Learning a Discriminative Feature Network for Semantic Segmentation
• Distance transform regression for spatially-aware deep semantic segmentation
• Look at Boundary: A Boundary-Aware Face Alignment Algorithm
• BoundarySqueeze: Image Segmentation as Boundary Squeezing
• Primitive Fitting Using Deep Boundary Aware Geometric Segmentation
• VLASE: Vehicle Localization by Aggregating Semantic Edges