Corpus ID: 43191745

Deep Category-Aware Semantic Edge Detection

  title={Deep Category-Aware Semantic Edge Detection},
  author={Zhiding Yu and Chen Feng and Ming-Yu Liu and Srikumar Ramalingam}
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… Expand

Figures and Tables from this paper

A Fully Convolutional Network-Based Tube Contour Detection Method Using Multi-Exposure Images
The experimental results show that the proposed fully convolutional network-based tube contour detection method can effectively improve the integrity and accuracy of tube contours detection in complex scenes. Expand
Semantic Edge Based Disparity Estimation Using Adaptive Dynamic Programming for Binocular Sensors
A robust sparse stereo matching method based on the semantic edges is proposed, which makes use of the disparity or semantic consistency constraint between the stereo images to adaptively search parameters, which can improve the robustness of the method. Expand
UPI-Net: Semantic Contour Detection in Placental Ultrasound
This paper investigates utero-placental interface (UPI) detection in 2D placental ultrasound images by formulating it as a semantic contour detection problem, and proposes a approach, namely UPI-Net, which aims to capture long-range dependencies in placenta geometry through lightweight global context modelling and effective multi-scale feature aggregation. Expand
Textual restoration of occluded Tibetan document pages based on side-enhanced U-Net
A side-enhanced U- net that attaches side feature extraction module and side classification module to the U-Net to improve the classification of textual edges is presented and experiments show that SEU-Net is able to classify the textual pixels in the occluded pages accurately. Expand
U-RISC: an ultra-high-resolution electron microscopy dataset challenging existing deep learning algorithms
It is found that in U-RISC, it requires a larger area around a pixel to predict whether the pixel belongs to the cell membrane or not, which is the largest cell membrane annotated Electron Microscopy dataset with a resolution of 2.18nm/pixel. Expand
Precise cable contour extraction method based on candidate point merge search
The experimental results show that this algorithm can extract the cable contour at pixel level without manual parameter setting, which is of great significance for cable quality detection. Expand


Semantic Segmentation with Boundary Neural Fields
A Boundary Neural Field (BNF) is introduced, which is a global energy model integrating FCN predictions with boundary cues that is used to enhance semantic segment coherence and to improve object localization. Expand
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Expand
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF). Expand
Supervised Learning of Edges and Object Boundaries
This paper proposes a novel supervised learning algorithm for edge and object boundary detection which it refers to as Boosted Edge Learning or BEL for short and shows applications for edge detection in a number of specific image domains as well as on natural images. Expand
Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform
This work proposes replacing the fully-connected CRF with domain transform (DT), a modern edge-preserving filtering method in which the amount of smoothing is controlled by a reference edge map, and shows that it yields comparable semantic segmentation results, accurately capturing object boundaries. Expand
Fully Convolutional Networks for Semantic Segmentation
It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation. Expand
Pushing the Boundaries of Boundary Detection using Deep Learning
This work shows that adapting Deep Convolutional Neural Network training to the task of boundary detection can result in substantial improvements over the current state-of-the-art in boundary detection, and examines the potential of the boundary detector in conjunction with thetask of semantic segmentation. Expand
High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and Its Applications to High-Level Vision
This work shows how to predict boundaries by exploiting object-level features from a pretrained object-classification network, and demonstrates that using their boundaries the authors improve the performance of state-of-the-art methods on the problems of semantic boundary labeling, semantic segmentation and object proposal generation. Expand
Learning Class-Specific Edges for Object Detection and Segmentation
It is shown how, for certain object classes, small regions around edges can be used to classify the edge into object or non-object, and performance of both algorithms (matching and segmentation) is considerably improved by the class-specific edge labelling. Expand
Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images
This work proposes algorithms for object boundary detection and hierarchical segmentation that generalize the gPb-ucm approach of [2] by making effective use of depth information and shows how this contextual information in turn improves object recognition. Expand