Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark

TL;DR

This paper introduces a dataset, standardized test conditions, and baseline benchmarks for feature coding in large models, addressing a key challenge in distributed deployment and fostering future research in this under-explored area.

Contribution

The paper provides the first comprehensive dataset, unified evaluation protocols, and baseline methods for feature coding in large models, facilitating standardized research and comparison.

Findings

Baseline methods achieve moderate performance on the dataset.

The dataset covers diverse features from multiple large models.

Standardized test conditions enable fair comparison across studies.

Abstract

Large models have achieved remarkable performance across various tasks, yet they incur significant computational costs and privacy concerns during both training and inference. Distributed deployment has emerged as a potential solution, but it necessitates the exchange of intermediate information between model segments, with feature representations serving as crucial information carriers. To optimize information exchange, feature coding is required to reduce transmission and storage overhead. Despite its importance, feature coding for large models remains an under-explored area. In this paper, we draw attention to large model feature coding and make three fundamental contributions. First, we introduce a comprehensive dataset encompassing diverse features generated by three representative types of large models. Second, we establish unified test conditions, enabling standardized evaluation pipelines and fair comparisons across future feature coding studies. Third, we introduce two baseline methods derived from widely used image coding techniques and benchmark their performance on the proposed dataset. These contributions aim to provide a foundation for future research and inspire broader engagement in this field. To support a long-term study, all source code and the dataset are made available at \href{https://github.com/chansongoal/LaMoFC}{https://github.com/chansongoal/LaMoFC}.