Corpus ID: 212717914

Partial Weight Adaptation for Robust DNN Inference

@article{Xie2020PartialWA,
  title={Partial Weight Adaptation for Robust DNN Inference},
  author={Xiufeng Xie and Kyu-Han Kim},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.06131}
}
  • Xiufeng Xie, Kyu-Han Kim
  • Published in ArXiv 2020
  • Computer Science, Engineering
  • Mainstream video analytics uses a pre-trained DNN model with an assumption that inference input and training data follow the same probability distribution. However, this assumption does not always hold in the wild: autonomous vehicles may capture video with varying brightness; unstable wireless bandwidth calls for adaptive bitrate streaming of video; and, inference servers may serve inputs from heterogeneous IoT devices/cameras. In such situations, the level of input distortion changes rapidly… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 22 REFERENCES

    Mask R-CNN

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Dilated Residual Networks

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    Multi-Scale Context Aggregation by Dilated Convolutions

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    Improving the Robustness of Deep Neural Networks via Stability Training

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Automatic differentiation in PyTorch

    VIEW 3 EXCERPTS

    Channel Pruning for Accelerating Very Deep Neural Networks

    • Yihui He, Xiangyu Zhang, Jian Sun
    • Computer Science
    • 2017 IEEE International Conference on Computer Vision (ICCV)
    • 2017
    VIEW 1 EXCERPT

    HTTP Live Streaming

    VIEW 1 EXCERPT