Deep architectures for image compression: a critical review
Deep learning architectures are now pervasive and filled almost all applications under
image processing, computer vision, and biometrics. The attractive property of feature …
image processing, computer vision, and biometrics. The attractive property of feature …
Autoregressive diffusion models
We introduce Autoregressive Diffusion Models (ARDMs), a model class encompassing and
generalizing order-agnostic autoregressive models (Uria et al., 2014) and absorbing …
generalizing order-agnostic autoregressive models (Uria et al., 2014) and absorbing …
Mood: Multi-level out-of-distribution detection
Abstract Out-of-distribution (OOD) detection is essential to prevent anomalous inputs from
causing a model to fail during deployment. While improved OOD detection methods have …
causing a model to fail during deployment. While improved OOD detection methods have …
End-to-end optimized versatile image compression with wavelet-like transform
Built on deep networks, end-to-end optimized image compression has made impressive
progress in the past few years. Previous studies usually adopt a compressive auto-encoder …
progress in the past few years. Previous studies usually adopt a compressive auto-encoder …
Practical full resolution learned lossless image compression
We propose the first practical learned lossless image compression system, L3C, and show
that it outperforms the popular engineered codecs, PNG, WebP and JPEG 2000. At the core …
that it outperforms the popular engineered codecs, PNG, WebP and JPEG 2000. At the core …
The impact of state-of-the-art techniques for lossless still image compression
A great deal of information is produced daily, due to advances in telecommunication, and
the issue of storing it on digital devices or transmitting it over the Internet is challenging. Data …
the issue of storing it on digital devices or transmitting it over the Internet is challenging. Data …
Integer discrete flows and lossless compression
E Hoogeboom, J Peters… - Advances in Neural …, 2019 - proceedings.neurips.cc
Lossless compression methods shorten the expected representation size of data without
loss of information, using a statistical model. Flow-based models are attractive in this setting …
loss of information, using a statistical model. Flow-based models are attractive in this setting …
Learning better lossless compression using lossy compression
We leverage the powerful lossy image compression algorithm BPG to build a lossless image
compression system. Specifically, the original image is first decomposed into the lossy …
compression system. Specifically, the original image is first decomposed into the lossy …
On the out-of-distribution generalization of probabilistic image modelling
Abstract Out-of-distribution (OOD) detection and lossless compression constitute two
problems that can be solved by the training of probabilistic models on a first dataset with …
problems that can be solved by the training of probabilistic models on a first dataset with …
DSSLIC: Deep semantic segmentation-based layered image compression
Deep learning has revolutionized many computer vision fields in the last few years,
including learning-based image compression. In this paper, we propose a deep semantic …
including learning-based image compression. In this paper, we propose a deep semantic …