DeepAI AI Chat
Log In Sign Up

Overfitting for Fun and Profit: Instance-Adaptive Data Compression

by   Ties van Rozendaal, et al.

Neural data compression has been shown to outperform classical methods in terms of RD performance, with results still improving rapidly. At a high level, neural compression is based on an autoencoder that tries to reconstruct the input instance from a (quantized) latent representation, coupled with a prior that is used to losslessly compress these latents. Due to limitations on model capacity and imperfect optimization and generalization, such models will suboptimally compress test data in general. However, one of the great strengths of learned compression is that if the test-time data distribution is known and relatively low-entropy (e.g. a camera watching a static scene, a dash cam in an autonomous car, etc.), the model can easily be finetuned or adapted to this distribution, leading to improved RD performance. In this paper we take this concept to the extreme, adapting the full model to a single video, and sending model updates (quantized and compressed using a parameter-space prior) along with the latent representation. Unlike previous work, we finetune not only the encoder/latents but the entire model, and - during finetuning - take into account both the effect of model quantization and the additional costs incurred by sending the model updates. We evaluate an image compression model on I-frames (sampled at 2 fps) from videos of the Xiph dataset, and demonstrate that full-model adaptation improves RD performance by  1 dB, with respect to encoder-only finetuning.


page 1

page 2

page 3

page 4


Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set

We introduce a video compression algorithm based on instance-adaptive le...

Lossy Image Compression with Quantized Hierarchical VAEs

Recent work has shown a strong theoretical connection between variationa...

L^2C – Learning to Learn to Compress

In this paper we present an end-to-end meta-learned system for image com...

Video Compression With Rate-Distortion Autoencoders

In this paper we present a a deep generative model for lossy video compr...

Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression

For neural video codec, it is critical, yet challenging, to design an ef...

Parametric context adaptive Laplace distribution for multimedia compression

Data compression often subtracts predictor and encodes the difference (r...

The Need for Medically Aware Video Compression in Gastroenterology

Compression is essential to storing and transmitting medical videos, but...