Unsupervised Learning of Edges

  title={Unsupervised Learning of Edges},
  author={Y. Li and Manohar Paluri and James M. Rehg and Piotr Doll{\'a}r},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Y. Li, Manohar Paluri, +1 author Piotr Dollár
  • Published 2016
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • Data-driven approaches for edge detection have proven effective and achieve top results on modern benchmarks. However, all current data-driven edge detectors require manual supervision for training in the form of hand-labeled region segments or object boundaries. Specifically, human annotators mark semantically meaningful edges which are subsequently used for training. Is this form of strong, highlevel supervision actually necessary to learn to accurately detect edges? In this work we present a… CONTINUE READING
    75 Citations
    Semi-supervised Learning of Instance-level Recognition from Video
    • PDF
    Deep Crisp Boundaries: From Boundaries to Higher-Level Tasks
    • 20
    • PDF
    Weakly supervised easy-to-hard learning for object detection in image sequences
    • PDF
    Object Boundary Detection and Classification with Image-Level Labels
    • 1
    • PDF
    Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks
    • 115
    • PDF
    Richer Convolutional Features for Edge Detection
    • 187
    • PDF
    Weakly Supervised Object Boundaries
    • 36
    • PDF
    Holistically-Nested Edge Detection
    • 143
    Learning Features by Watching Objects Move
    • 314
    • PDF
    Supervision by Fusion: Towards Unsupervised Learning of Deep Salient Object Detector
    • 63
    • PDF


    Fast Edge Detection Using Structured Forests
    • 620
    • PDF
    Supervised Learning of Edges and Object Boundaries
    • 452
    • PDF
    Learning object class detectors from weakly annotated video
    • 404
    • PDF
    Unsupervised Visual Representation Learning by Context Prediction
    • 1,053
    • PDF
    Learning to detect Motion Boundaries
    • 50
    • Highly Influential
    • PDF
    High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and Its Applications to High-Level Vision
    • 114
    • PDF
    Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection
    • 347
    • PDF
    Discriminatively Trained Sparse Code Gradients for Contour Detection
    • 214
    • PDF
    Learning to detect natural image boundaries using local brightness, color, and texture cues
    • 2,263
    • Highly Influential
    • PDF
    Visual Boundary Prediction: A Deep Neural Prediction Network and Quality Dissection
    • 66
    • PDF