Published on Thu Nov 19 2020

Unmixing Convolutional Features for Crisp Edge Detection

Linxi Huan, Nan Xue, Xianwei Zheng, Wei He, Jianya Gong, Gui-Song Xia

The proposed CATS can be integrated into modern deep edge detectors to improve localization accuracy. With the vanilla VGG16 backbone, in terms of BSDS500 dataset, our CATS improves the F-measure (ODS) of the RCF and BDCN deep edge detector

2
0
0
Abstract

This paper presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly caused by the mixing phenomenon of convolutional neural networks: feature mixing in edge classification and side mixing during fusing side predictions. The CATS consists of two modules: a novel tracing loss that performs feature unmixing by tracing boundaries for better side edge learning, and a context-aware fusion block that tackles the side mixing by aggregating the complementary merits of learned side edges. Experiments demonstrate that the proposed CATS can be integrated into modern deep edge detectors to improve localization accuracy. With the vanilla VGG16 backbone, in terms of BSDS500 dataset, our CATS improves the F-measure (ODS) of the RCF and BDCN deep edge detectors by 12% and 6% respectively when evaluating without using the morphological non-maximal suppression scheme for edge detection.

Mon Aug 16 2021our pick
Computer Vision
Pixel Difference Networks for Efficient Edge Detection
Deep Convolutional Neural Networks (CNNs) can achieve human-level performance in edge detection. The previous wisdom from the traditional edge detectors, such as Canny, Sobel, and LBP are rarely investigated in the rapid-developing deep learning era. We propose a simple,
1
0
0
Wed Sep 04 2019
Machine Learning
Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection
This paper proposes a Deep Learning based edge detector, which is inspired on HED (Holistically-Nested Edge Detection) and Xception networks. The proposed approach generates thin edge-maps that are plausible for human eyes.
0
0
0
Wed Dec 07 2016
Computer Vision
Richer Convolutional Features for Edge Detection
We propose an accurate edge detector using richer convolutional features (RCF) Since objects in nature images have various.scales and aspect ratios, the automatically learned rich hierarchical representations by CNNs are very. critical and effective to detect edges andobject boundaries.
0
0
0
Fri Apr 24 2015
Computer Vision
Holistically-Nested Edge Detection
We develop a new edge detection algorithm that tackles two important issues in this long-standing vision problem. Our proposed method, holistically-nested edge detection (HED), performs image-to-image prediction by means of a deep learning model. HED automatically learns rich
0
0
0
Tue Dec 15 2020
Computer Vision
FINED: Fast Inference Network for Edge Detection
0
0
0
Thu Feb 28 2019
Computer Vision
Bi-Directional Cascade Network for Perceptual Edge Detection
We propose a Bi-Directional Cascade Network (BDCN) structure. An individual layer is supervised by labeled edges at its specific scale. We evaluate our method on three datasets, i.e., BSDS500, NYUDv2, and Multicue.
0
0
0
Thu Sep 04 2014
Computer Vision
Very Deep Convolutional Networks for Large-Scale Image Recognition
Convolutional networks of increasing depth can achieve state-of-the-art results. The research was the basis of the team's ImageNet Challenge 2014.
2
2
7
Tue Feb 10 2015
Machine Learning
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
We introduce an attention based model that automatically learns to describe the content of images. We validate the use of attention with state-of-the-art performance on three benchmark datasets.
2
1
2
Tue Mar 15 2016
Machine Learning
Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
We develop a deep learning algorithm for contour detection with a fully convolutional encoder-decoder network. Different from previous low-level edge detection, our algorithm focuses on detecting higher-level object contours.
0
0
0
Tue May 31 2016
Machine Learning
Dynamic Filter Networks
In a traditional convolutional layer, the learned filters stay fixed after training. In contrast, we introduce a new framework, the Dynamic Filter Network, where filters are generated dynamically conditioned on an input. We demonstrate the effectiveness of the dynamic filter network on the tasks of video and stereo prediction.
0
0
0
Tue Dec 02 2014
Computer Vision
DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection
Contour detection has been a fundamental component in many image segmentation and object detection systems. We claim that recognizing objects and predicting contours are two mutually related tasks. We show that without any feature engineering our multi-scale deep learning approach achieves state-of-the-art results in contour detection.
0
0
0
Mon Feb 25 2019
Computer Vision
Dynamic Feature Fusion for Semantic Edge Detection
The prevalent semantic edge detection methods apply a fixed weight fusion strategy. We propose a novel dynamic feature fusion strategy that assigns different fusion weights for different input images and locations. This is achieved by a proposed weight learner to infer proper fusion weights over multi-level features.
0
0
0