EDTER: Edge Detection with Transformer
Authors:
Top Cited Papers
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1392-1402
Abstract
Convolutional neural networks have made significant progresses in edge detection by progressively exploring the context and semantic features. However, local details are gradually suppressed with the enlarging of receptive fields. Recently, vision transformer has shown excellent capability in capturing long-range dependencies. Inspired by this, we propose a novel transformer-based edge detector, Edge Detection TransformER (EDTER), to extract clear and crisp object boundaries and meaningful edges by exploiting the full image context information and detailed local cues simultaneously. EDTER works in two stages. In Stage I, a global transformer encoder is used to capture long-range global context on coarse-grained image patches. Then in Stage II, a local transformer encoder works on fine-grained patches to excavate the short-range local cues. Each transformer encoder is followed by an elaborately designed Bi-directional Multi-Level Aggregation decoder to achieve high-resolution features. Finally, the global context and local cues are combined by a Feature Fusion Module and fed into a decision head for edge prediction. Extensive experiments on BSDS500, NYUDv2, and Multicue demonstrate the superiority of EDTER in comparison with state-of-the-arts. The source code is available at https://github.com/MengyangPu/EDTER.Keywords
All Related Versions
Funding Information
- Beijing Natural Science Foundation (M22022,L211015)
- Fundamental Research Funds for the Central Universities (2019JBZ104)
- National Natural Science Foundation of China (61906013,62106017)
This publication has 54 references indexed in Scilit:
- Multiscale Centerline DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Fully convolutional networks for semantic segmentation2015
- Fast Edge Detection Using Structured ForestsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images2013
- Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection2013
- XDoG: An eXtended difference-of-Gaussians compendium including advanced image stylizationComputers & Graphics, 2012
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004
- Learning to detect natural image boundaries using local brightness, color, and texture cuesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- On the accuracy of the Sobel edge detectorImage and Vision Computing, 1983