Self-Supervised Variable Rate Image Compression Using Visual Attention

Abhishek Kumar Sinha, S. Manthira Moorthi, Debajyoti Dhar; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 1721-1725

Abstract


The recent success of self-supervised learning relies on its ability to learn the representations from self-defined pseudo-labels that are applied to several downstream tasks. Motivated by this ability, we present a deep image compression technique, which learns the lossy reconstruction of raw images from the self-supervised learned representation of SimCLR ResNet-50 architecture. Our framework uses a feature pyramid to achieve the variable rate compression of the image using a self-attention map for the optimal allocation of bits. The paper provides an overview to observe the effects of contrastive self-supervised representations and the self-attention map on the distortion and perceptual quality of the reconstructed image. The experiments are performed on a different class of images to show that the proposed method outperforms the other variable rate deep compression models without compromising the perceptual quality of the images.

Related Material


[pdf]
[bibtex]
@InProceedings{Sinha_2022_CVPR, author = {Sinha, Abhishek Kumar and Moorthi, S. Manthira and Dhar, Debajyoti}, title = {Self-Supervised Variable Rate Image Compression Using Visual Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {1721-1725} }