End-to-End Learnable Multi-Scale Feature Compression for VCM

TL;DR

This paper introduces an end-to-end learnable multi-scale feature compression method optimized for machine vision, significantly reducing bitrate and encoding time compared to previous approaches.

Contribution

It proposes a novel integrated compression and fusion model that enables end-to-end training and lightweight encoding for multi-scale features in VCM.

Findings

Achieves at least 52% BD-rate reduction over previous methods.

Reduces encoding time by 5 to 27 times.

Outperforms existing approaches in feature compression efficiency.

Abstract

The proliferation of deep learning-based machine vision applications has given rise to a new type of compression, so called video coding for machine (VCM). VCM differs from traditional video coding in that it is optimized for machine vision performance instead of human visual quality. In the feature compression track of MPEG-VCM, multi-scale features extracted from images are subject to compression. Recent feature compression works have demonstrated that the versatile video coding (VVC) standard-based approach can achieve a BD-rate reduction of up to 96% against MPEG-VCM feature anchor. However, it is still sub-optimal as VVC was not designed for extracted features but for natural images. Moreover, the high encoding complexity of VVC makes it difficult to design a lightweight encoder without sacrificing performance. To address these challenges, we propose a novel multi-scale feature compression method that enables both the end-to-end optimization on the extracted features and the design of lightweight encoders. The proposed model combines a learnable compressor with a multi-scale feature fusion network so that the redundancy in the multi-scale features is effectively removed. Instead of simply cascading the fusion network and the compression network, we integrate the fusion and encoding processes in an interleaved way. Our model first encodes a larger-scale feature to obtain a latent representation and then fuses the latent with a smaller-scale feature. This process is successively performed until the smallest-scale feature is fused and then the encoded latent at the final stage is entropy-coded for transmission. The results show that our model outperforms previous approaches by at least 52% BD-rate reduction and has $\times5$ to $\times27$ times less encoding time for object detection...