Holistically-Nested Edge Detection

@article{Xie2015HolisticallyNestedED,
  title={Holistically-Nested Edge Detection},
  author={Saining Xie and Zhuowen Tu},
  journal={International Journal of Computer Vision},
  year={2015},
  volume={125},
  pages={3-18}
}
  • Saining XieZ. Tu
  • Published 23 April 2015
  • Computer Science
  • International Journal of Computer Vision
We develop a new edge detection algorithm that addresses two important issues in this long-standing vision problem: (1) holistic image training and prediction; and (2) multi-scale and multi-level feature learning. [] Key Method HED automatically learns rich hierarchical representations (guided by deep supervision on side responses) that are important in order to resolve the challenging ambiguity in edge and object boundary detection. We significantly advance the state-of-the-art on the BSDS500 dataset (ODS F…
[PDF] Semantic Reader
2,623 Citations
Highly Influential Citations
480
Background Citations
1,052
Methods Citations
1,281
Results Citations
53

2,623 Citations

Iterative Residual Network for Structured Edge Detection

This work proposes a novel Iterative Residual Holistically-nested Edge Detection (IRHED) network, which incorporates multi-scale features from the hierarchy of the network, and learns to iteratively refine the output boundary map in a deeply supervised manner.

Richer Convolutional Features for Edge Detection

RCF encapsulates all convolutional features into more discriminative representation, which makes good usage of rich feature hierarchies, and is amenable to training via backpropagation, and achieves state-of-the-art performance on several available datasets.

Deeply Supervised Salient Object Detection with Short Connections

This paper proposes a new salient object detection method by introducing short connections to the skip-layer structures within the HED architecture, which takes full advantage of multi-level and multi-scale features extracted from FCNs, providing more advanced representations at each layer, a property that is critically needed to perform segment detection.

Prominent edge detection with deep metric expression and multi-scale features

Simulations and comparisons on benchmark datasets demonstrate the proposed semantic edge detection algorithm is superior to the others through visual and quantitative evaluation, and specifically, the score of ODS reachs 0.788.

Richer Convolutional Features for Edge Detection

The proposed network fully exploits multiscale and multilevel information of objects to perform the image-to-image prediction by combining all the meaningful convolutional features in a holistic manner and achieves state-of-the-art performance on several available datasets.

Cumulative Nets for Edge Detection

A Cumulative Network (C-Net), which learns the side network cumulatively based on current visual features and low-level side outputs, to gradually remove detailed or sharp boundaries to enable high-resolution and accurate edge detection.

Bidirectional Multiscale Refinement Network for Crisp Edge Detection

This work introduces a novel parallel attention model and a novel loss function that combines cross-entropy and dice loss through the use of adaptive coefficients, and proposes a novel bidirectional multiscale refinement network (BMRN) that stacks multiple refinement modules in order to achieve richer feature representation.

DeepEdgeNet: Edge Detection With EfficientNets. Category: Computer Vision

This paper intends to use the learnings from DexiNed, HED, and CASEnet to explore, investigate, and build a robust deep neural network for holistic and reliable edge detection in images.

Learning Deep Structured Multi-scale Features for Crisp and Object Occlusion Edge Detection

This paper proposes a novel method of edge detection called MSDF (Multi Scale Decode and Fusion) based on deep structured multi-scale features to generate crisp salient edges and surpass the state of the art on the BSDS ownership dataset in occlusion edge detection.

R-CASENet: A Multi-category Edge Detection Network

This paper presents an accurate multi-category edge detection network Richer-CASENet (R-CasENet), which attempts to make full use of CNN’s powerful feature expression capabilities for edge feature extraction and classification.
...

References

SHOWING 1-10 OF 61 REFERENCES

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%.

Fast Edge Detection Using Structured Forests

This paper forms the problem of predicting local edge masks in a structured learning framework applied to random decision forests and develops a novel approach to learning decision trees robustly maps the structured labels to a discrete space on which standard information gain measures may be evaluated.

DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection

This work shows that contour detection accuracy can be improved by instead making the use of the deep features learned from convolutional neural networks (CNNs), while rather than using the networks as a blackbox feature extractor, it customize the training strategy by partitioning contour (positive) data into subclasses and fitting each subclass by different model parameters.

Object Contour Detection with a Fully Convolutional Encoder-Decoder Network

A deep learning algorithm for contour detection with a fully convolutional encoder-decoder network that generalizes well to unseen object classes from the same supercategories on MS COCO and can match state-of-the-art edge detection on BSDS500 with fine-tuning.

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.

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.

Unsupervised Learning of Edges

This work presents a simple yet effective approach for training edge detectors without human supervision, and shows that when using a deep network for the edge detector, this approach provides a novel pre-training scheme for object detection.

Visual Boundary Prediction: A Deep Neural Prediction Network and Quality Dissection

A novel neurally-inspired deep architecture is developed for visual boundary detection, i.e. prediction of the presence of a boundary at a given image location, with comparable or better performance to topperforming methods with eective inference times.

Deeply-Supervised Nets

The proposed deeply-supervised nets (DSN) method simultaneously minimizes classification error while making the learning process of hidden layers direct and transparent, and extends techniques from stochastic gradient methods to analyze the algorithm.

Learning Rich Features from RGB-D Images for Object Detection and Segmentation

A new geocentric embedding is proposed for depth images that encodes height above ground and angle with gravity for each pixel in addition to the horizontal disparity to facilitate the use of perception in fields like robotics.
...