Compressing Weight-updates for Image Artifacts Removal Neural Networks

Yat Hong Lam, Alireza Zare, Caglar Aytekin, Francesco Cricri, Jani Lainema, Emre Aksu, Miska Hannuksela; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 0-0

Abstract


In this paper, we present a novel approach for fine-tuning a decoder-side neural network in the context of image compression, such that the weight-updates are better compressible. At encoder side, we fine-tune a pre-trained artifact removal network on target data by using a compression objective applied on the weight-update. In particular, the compression objective encourages weight-updates which are sparse and closer to quantized values. This way, the final weight-update can be compressed more efficiently by pruning and quantization, and can be included into the encoded bitstream together with the image bitstream of a traditional codec. We show that this approach achieves reconstruction quality which is on-par or slightly superior to a traditional codec, at comparable bitrates. To our knowledge, this is the first attempt to combine image compression and neural network's weight update compression.

Related Material


[pdf]
[bibtex]
@InProceedings{Lam_2019_CVPR_Workshops,
author = {Hong Lam, Yat and Zare, Alireza and Aytekin, Caglar and Cricri, Francesco and Lainema, Jani and Aksu, Emre and Hannuksela, Miska},
title = {Compressing Weight-updates for Image Artifacts Removal Neural Networks},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}