Attention to Scale: Scale-Aware Semantic Image Segmentation

  title={Attention to Scale: Scale-Aware Semantic Image Segmentation},
  author={Liang-Chieh Chen and Y. Yang and Jiang Wang and Wei Xu and A. Yuille},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Liang-Chieh Chen, Y. Yang, +2 authors A. Yuille
  • Published 2016
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • Incorporating multi-scale features in fully convolutional neural networks (FCNs) has been a key element to achieving state-of-the-art performance on semantic image segmentation. [...] Key Method We adapt a state-of-the-art semantic image segmentation model, which we jointly train with multi-scale input images and the attention model. The proposed attention model not only outperforms averageand max-pooling, but allows us to diagnostically visualize the importance of features at different positions and scales…Expand Abstract
    Rethinking Atrous Convolution for Semantic Image Segmentation
    • 1,701
    • PDF
    RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
    • 1,052
    • PDF
    Residual Attention Network for Image Classification
    • 992
    • PDF
    Multi-Scale Context Aggregation by Dilated Convolutions
    • 3,446
    • Highly Influenced
    • PDF
    Fully Convolutional Neural Networks with Full-Scale-Features for Semantic Segmentation
    • 11
    • PDF
    Semantic Image Segmentation Based on Attentions to Intra Scales and Inner Channels
    • 2
    • Highly Influenced
    Multi-scale deep context convolutional neural networks for semantic segmentation
    • 55
    • PDF


    Publications referenced by this paper.
    Fully Convolutional Networks for Semantic Segmentation
    • 7,207
    • Highly Influential
    • PDF
    Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
    • 11,444
    • PDF
    Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
    • 2,440
    • PDF
    Holistically-Nested Edge Detection
    • 1,423
    • PDF
    Learning Deconvolution Network for Semantic Segmentation
    • 1,417
    • PDF
    Learning Hierarchical Features for Scene Labeling
    • 2,067
    • PDF