Weakly Supervised Scene Parsing with Point-based Distance Metric Learning

  title={Weakly Supervised Scene Parsing with Point-based Distance Metric Learning},
  author={Rui Qian and Yunchao Wei and Honghui Shi and Jiachen Li and Jiaying Liu and Thomas S. Huang},
  • Rui Qian, Yunchao Wei, +3 authors Thomas S. Huang
  • Published in AAAI 2019
  • Computer Science
  • Semantic scene parsing is suffering from the fact that pixel-level annotations are hard to be collected. To tackle this issue, we propose a Point-based Distance Metric Learning (PDML) in this paper. PDML does not require dense annotated masks and only leverages several labeled points that are much easier to obtain to guide the training process. Concretely, we leverage semantic relationship among the annotated points by encouraging the feature representations of the intra- and inter-category… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Twitter Mentions


    Publications referenced by this paper.

    Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions

    Adversarial Complementary Learning for Weakly Supervised Object Localization

    Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation

    Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach

    Recurrent Pixel Embedding for Instance Grouping

    STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation

    Scene Parsing through ADE20K Dataset

    SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation