Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

computer-vision-7

Contour Detection

3260 papers • 126 benchmarks • 313 datasets

Object Contour Detection extracts information about the object shape in images. Source: Object Contour and Edge Detection with RefineContourNet

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in contour-detection-7

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find contour-detection-7 models and implementations

Datasets

ICDAR 2021

Subtasks

No subtasks available.

Most implemented papers

Object Contour Detection with a Fully Convolutional Encoder-Decoder Network

Honglak Lee, Ming-Hsuan Yang, Jimei Yang, Scott D. Cohen, Brian L. Price•Mon Mar 14 2016

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.

385

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks

J. Pont-Tuset, Kevis-Kokitsi Maninis, P. Arbeláez, L. Van Gool•Mon Aug 08 2016

Convolutional Oriented Boundaries gives a significant leap in performance over the state-of-the-art, and generalizes very well to unseen categories and datasets, and learning to estimate not only contour strength but also orientation provides more accurate results.

246 0

Paper Graph

Object Contour and Edge Detection with RefineContourNet

A. Kelm, V. S. Rao, U. Zölzer•Mon Apr 29 2019

A ResNet-based multi-path refinement CNN is used for object contour detection to prioritise the effective utilization of the high-level abstraction capability of a ResNet, which leads to state-of-the-art results for edge detection.

48 0

Paper Graph

Learning long-range spatial dependencies with horizontal gated-recurrent units

Thomas Serre, Drew Linsley, Junkyung Kim, Vijay Veerabadran•Sun May 20 2018

This work introduces the horizontal gated-recurrent unit (hGRU) to learn intrinsic horizontal connections -- both within and across feature columns, and demonstrates that a single hGRU layer matches or outperforms all tested feedforward hierarchical baselines including state-of-the-art architectures which have orders of magnitude more free parameters.

171 0

Paper Graph

Contour Knowledge Transfer for Salient Object Detection

D. Shen, F. Yang, W. Liu, Xin Li, Hong Cheng•Fri Sep 07 2018

A contour-to-saliency transferring method to automatically generate salient object masks which can be used to train the saliency branch from outputs of the contour branch, and introduces a novel alternating training pipeline to gradually update the network parameters.

266 0

Paper Graph

Psi-Net: Shape and boundary aware joint multi-task deep network for medical image segmentation

Balamurali Murugesan, Sharath M. Shankaranarayana, Kaushik Sarveswaran, K. Ram, M. Sivaprakasam•Sun Feb 10 2019

This work proposes a novel architecture called Psi-Net with a single encoder and three parallel decoders to facilitate joint training of three tasks, and proposes a new joint loss function which consists of a weighted combination of Negative Log Likelihood and Mean Square Error loss.

177 0

Paper Graph

A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision

Huchuan Lu, Errui Ding, Dong Wang, Wenlong Guan, Runmin Wu, Mengyang Feng•Fri May 31 2019

This work proposes to train saliency detection networks by exploiting the supervision from not only salient object detection, but also foreground contour detection and edge detection, and develops a novel mutual learning module (MLM), which improves the performance by a large margin.

236 0

Paper Graph

Contour Integration using Graph-Cut and Non-Classical Receptive Field

Seyedeh-Zahra Mousavi Kouzehkanan, Reshad Hosseini, Babak Nadjar Araabi•Mon Oct 26 2020

This paper proposes a novel method to detect image contours from the extracted edge segments of other algorithms based on an undirected graphical model with the edge segments set as the vertices that can improve extracting the binary map.

0 0

Paper Graph

Adding a benchmark result helps the community track progress.

Contour Detection | State-of-the-Art