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

Ties van Rozendaal, Johann Brehmer, Yunfan Zhang, Reza Pourreza, Taco Cohen

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

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 low-latency scale-space flow model by between 24% and 26% 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 on compression models. We show that it enables a state-of-the-art performance even after reducing the network size by 72%.

One-sentence Summary: We improve neural video compression by finetuning a model on each sequence and compressing the model updates efficiently.