# Lossy Image Compression with Compressive Autoencoders Source: [Lossy Image Compression with Compressive Autoencoders]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:35:17.063Z Authors: Lucas Theis, Wenzhe Shi, Andrew Cunningham, Ferenc Husz\\'ar Published: 2017-03-01T17:13:47.000Z ## Abstract We propose a new approach to the problem of optimizing autoencoders for lossy image compression. New media formats, changing hardware technology, as well as diverse requirements and content types create a need for compression algorithms which are more flexible than existing codecs. Autoencoders have the potential to address this need, but are difficult to optimize directly due to the inherent non-differentiabilty of the compression loss. We here show that minimal changes to the loss are sufficient to train deep autoencoders competitive with JPEG 2000 and outperforming recently proposed approaches based on RNNs. Our network is furthermore computationally efficient thanks to a sub-pixel architecture, which makes it suitable for high-resolution images. This is in contrast to previous work on autoencoders for compression using coarser approximations, shallower architectures, computationally expensive methods, or focusing on small images. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on ImageNet (val) (Top-1/Top-5 Accuracy)](): Image Classification; ImageNet (val); Top-1 Accuracy: 69.74. - [Neural Architecture Search on ImageNet (train)](): Neural Architecture Search; ImageNet (train); GPU Days (GPUD): not recorded. ## Original sources and implementation [Original paper]() [PDF]()