Parameter-Efficient Instance-Adaptive Neural Video Compression

TL;DR

This paper introduces a lightweight, parameter-efficient fine-tuning approach for neural video codecs that enhances compression performance and robustness while reducing computational costs and training instability.

Contribution

It proposes a novel adapter-based fine-tuning method for neural video codecs, improving efficiency and performance over existing instance-adaptive techniques.

Findings

Significant improvement in rate-distortion performance (up to 5 dB PSNR)

Reduced encoding time compared to existing methods

Enhanced training robustness and stability

Abstract

Learning-based Neural Video Codecs (NVCs) have emerged as a compelling alternative to standard video codecs, demonstrating promising performance, and simple and easily maintainable pipelines. However, NVCs often fall short of compression performance and occasionally exhibit poor generalization capability due to inference-only compression scheme and their dependence on training data. The instance-adaptive video compression techniques have recently been suggested as a viable solution, fine-tuning the encoder or decoder networks for a particular test instance video. However, fine-tuning all the model parameters incurs high computational costs, increases the bitrates, and often leads to unstable training. In this work, we propose a parameter-efficient instance-adaptive video compression framework. Inspired by the remarkable success of parameter-efficient fine-tuning on large-scale neural network models, we propose to use a lightweight adapter module that can be easily attached to the pretrained NVCs and fine-tuned for test video sequences. The resulting algorithm significantly improves compression performance and reduces the encoding time compared to the existing instant-adaptive video compression algorithms. Furthermore, the suggested fine-tuning method enhances the robustness of the training process, allowing for the proposed method to be widely used in many practical settings. We conducted extensive experiments on various standard benchmark datasets, including UVG, MCL-JVC, and HEVC sequences, and the experimental results have shown a significant improvement in rate-distortion (RD) curves (up to 5 dB PSNR) and BD rates compared to the baselines NVC. Our code is available on https://github.com/ohsngjun/PEVC.