CASENet: Deep Category-Aware Semantic Edge Detection

05/27/2017
by   Zhiding Yu, et al.
0

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.

READ FULL TEXT

page 1

page 4

page 7

page 8

page 11

page 13

page 14

page 15

research
03/29/2020

Adaptive Object Detection with Dual Multi-Label Prediction

In this paper, we propose a novel end-to-end unsupervised deep domain ad...
research
04/09/2018

Semantic Edge Detection with Diverse Deep Supervision

Semantic edge detection (SED), which aims at jointly extracting edges as...
research
04/08/2022

Semantic Representation and Dependency Learning for Multi-Label Image Recognition

Recently many multi-label image recognition (MLR) works have made signif...
research
03/18/2023

Edge-aware Plug-and-play Scheme for Semantic Segmentation

Semantic segmentation is a classic and fundamental computer vision probl...
research
04/11/2022

Category-Aware Transformer Network for Better Human-Object Interaction Detection

Human-Object Interactions (HOI) detection, which aims to localize a huma...
research
07/06/2018

VLASE: Vehicle Localization by Aggregating Semantic Edges

In this paper, we propose VLASE, a framework to use semantic edge featur...
research
04/22/2021

Neuro-inspired edge feature fusion using Choquet integrals

It is known that the human visual system performs a hierarchical informa...

Please sign up or login with your details

Forgot password? Click here to reset