Corpus ID: 215826266

Learning multiple visual domains with residual adapters

@inproceedings{Rebuffi2017LearningMV,
  title={Learning multiple visual domains with residual adapters},
  author={Sylvestre-Alvise Rebuffi and Hakan Bilen and A. Vedaldi},
  booktitle={NIPS},
  year={2017}
}
  • Sylvestre-Alvise Rebuffi, Hakan Bilen, A. Vedaldi
  • Published in NIPS 2017
  • Computer Science, Mathematics
  • There is a growing interest in learning data representations that work well for many different types of problems and data. In this paper, we look in particular at the task of learning a single visual representation that can be successfully utilized in the analysis of very different types of images, from dog breeds to stop signs and digits. Inspired by recent work on learning networks that predict the parameters of another, we develop a tunable deep network architecture that, by means of adapter… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Deep Visual Domain Adaptation: A Survey
    • 317
    • PDF
    SMASH: One-Shot Model Architecture Search through HyperNetworks
    • 317
    • PDF
    Efficient Parametrization of Multi-domain Deep Neural Networks
    • 92
    • PDF
    Group Normalization
    • 650
    • PDF
    Meta-learning with differentiable closed-form solvers
    • 144
    • PDF
    BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
    • 130
    • PDF
    Episodic Training for Domain Generalization
    • 53
    • Highly Influenced
    • PDF
    Deep Learning for Generic Object Detection: A Survey
    • 301
    • PDF
    End-To-End Multi-Task Learning With Attention
    • 85
    • Highly Influenced
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 48 REFERENCES
    Learning Multiple Layers of Features from Tiny Images
    • 9,107
    • PDF
    Identity Mappings in Deep Residual Networks
    • 3,892
    • PDF
    Learning without Forgetting
    • 743
    • PDF
    Wide Residual Networks
    • 2,318
    • PDF
    ImageNet Large Scale Visual Recognition Challenge
    • 16,498
    • PDF
    Unsupervised Domain Adaptation by Backpropagation
    • 1,694
    • PDF