-
Deep Residual Learning in the JPEG Transform Domain
AbstractWe introduce a general method of performing Residual Network inference and learning in the JPEG transform domain that allows the network to consume compressed images as input. Our formulation leverages the linearity of the JPEG transform to redefine convolution and batch normalization with a tune-able numerical approximation for ReLu. The result is mathematically equivalent to the spatial domain network up to the ReLu approximation accuracy. A formulation for image classification and a model conversion algorithm for spatial domain networks are given as examples of the method. We show that the sparsity of the JPEG format allows for faster processing of images with little to no penalty in the network accuracy.
Related Material
[pdf] [supp][bibtex]@InProceedings{Ehrlich_2019_ICCV,
author = {Ehrlich, Max and Davis, Larry S.},
title = {Deep Residual Learning in the JPEG Transform Domain},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}
These ICCV 2019 papers are the Open Access versions, provided by the Computer Vision Foundation.
Except for the watermark, they are identical to the accepted versions; the final published version of the proceedings is available on IEEE Xplore.
Except for the watermark, they are identical to the accepted versions; the final published version of the proceedings is available on IEEE Xplore.
This material is presented to ensure timely dissemination of scholarly and technical work.
Copyright and all rights therein are retained by authors or by other copyright holders.
All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright.