Referring Image Segmentation by Generative Adversarial Learning

  title={Referring Image Segmentation by Generative Adversarial Learning},
  author={Shuang Qiu and Y. Zhao and Jianbo Jiao and Yunchao Wei and S. Wei},
  journal={IEEE Transactions on Multimedia},
  • Shuang Qiu, Y. Zhao, +2 authors S. Wei
  • Published 2020
  • Computer Science
  • IEEE Transactions on Multimedia
  • Referring expression is a kind of language expression being used for referring to particular objects. In this paper, we focus on the problem of image segmentation from natural language referring expressions. Existing works tackle this problem by augmenting the convolutional semantic segmentation networks with an LSTM sentence encoder, which is optimized by a pixel-wise classification loss. We argue that the distribution similarity between the inference and ground truth plays an important role… CONTINUE READING
    5 Citations

    Figures, Tables, and Topics from this paper

    Explore Further: Topics Discussed in This Paper

    Referring Image Segmentation via Cross-Modal Progressive Comprehension
    • 4
    • PDF
    Referring Expression Comprehension: A Survey of Methods and Datasets
    • PDF
    Linguistic Structure Guided Context Modeling for Referring Image Segmentation
    • 2
    • PDF


    Semantic Segmentation using Adversarial Networks
    • 431
    • PDF
    Context Encoders: Feature Learning by Inpainting
    • 2,208
    • PDF
    Recurrent Multimodal Interaction for Referring Image Segmentation
    • 43
    • Highly Influential
    • PDF
    Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach
    • 303
    • PDF
    Grounding of Textual Phrases in Images by Reconstruction
    • 293
    • PDF
    Segmentation from Natural Language Expressions
    • 110
    • Highly Influential
    • PDF
    Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation
    • 174
    • PDF