Corpus ID: 218763610

Interpretable and Accurate Fine-grained Recognition via Region Grouping

@article{Huang2020InterpretableAA,
  title={Interpretable and Accurate Fine-grained Recognition via Region Grouping},
  author={Zixuan Huang and Yanchao Li},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.10411}
}
  • Zixuan Huang, Yanchao Li
  • Published 2020
  • Computer Science
  • ArXiv
  • We present an interpretable deep model for fine-grained visual recognition. At the core of our method lies the integration of region-based part discovery and attribution within a deep neural network. Our model is trained using image-level object labels, and provides an interpretation of its results via the segmentation of object parts and the identification of their contributions towards classification. To facilitate the learning of object parts without direct supervision, we explore a simple… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 72 REFERENCES

    Part-Stacked CNN for Fine-Grained Visual Categorization

    VIEW 1 EXCERPT

    Learning to Navigate for Fine-grained Classification

    VIEW 1 EXCERPT

    Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks

    VIEW 1 EXCERPT

    The application of two-level attention models in deep convolutional neural network for fine-grained image classification

    • Tianjun Xiao, Yichong Xu, +3 authors Zheng Zhang
    • Computer Science
    • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2015
    VIEW 2 EXCERPTS

    Picking Deep Filter Responses for Fine-Grained Image Recognition

    VIEW 1 EXCERPT