Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set
arXiv:2111.10302
Abstract
We introduce a video compression algorithm based on instance-adaptive learning. On each video sequence to be transmitted, we finetune a pretrained compression model. The optimal parameters are transmitted to the receiver along with the latent code. By entropy-coding the parameter updates under a suitable mixture model prior, we ensure that the network parameters can be encoded efficiently. This instance-adaptive compression algorithm is agnostic about the choice of base model and has the potential to improve any neural video codec. On UVG, HEVC, and Xiph datasets, our codec improves the performance of a scale-space flow model by between 21% and 27% BD-rate savings, and that of a state-of-the-art B-frame model by 17 to 20% BD-rate savings. We also demonstrate that instance-adaptive finetuning improves the robustness to domain shift. Finally, our approach reduces the capacity requirements of compression models. We show that it enables a competitive performance even after reducing the network size by 70%.
arXiv commentMatches version published in TMLR
References in corpus (9)
- Auto-Encoding Variational Bayes
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Video Compression With Rate-Distortion Autoencoders
- Learning for Video Compression
- Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model
- Improving Inference for Neural Image Compression
- Overfitting for Fun and Profit: Instance-Adaptive Data Compression
- Compressing Weight-updates for Image Artifacts Removal Neural Networks
- A Compression Objective and a Cycle Loss for Neural Image Compression