DMOFC: Discrimination Metric-Optimized Feature Compression

TL;DR

This paper introduces a discrimination metric for feature compression in video coding for machines, emphasizing inter-feature relationships to preserve feature discriminability, and demonstrates its effectiveness through experiments.

Contribution

The paper proposes a novel discrimination metric that considers inter-feature relationships, improving feature discriminability in compression, which was neglected in prior intra-feature focused methods.

Findings

The discrimination metric effectively maintains feature discriminability.

There is a trade-off between the discrimination metric and original feature discriminability.

Experimental results validate the proposed method's effectiveness.

Abstract

Feature compression, as an important branch of video coding for machines (VCM), has attracted significant attention and exploration. However, the existing methods mainly focus on intra-feature similarity, such as the Mean Squared Error (MSE) between the reconstructed and original features, while neglecting the importance of inter-feature relationships. In this paper, we analyze the inter-feature relationships, focusing on feature discriminability in machine vision and underscoring its significance in feature compression. To maintain the feature discriminability of reconstructed features, we introduce a discrimination metric for feature compression. The discrimination metric is designed to ensure that the distance between features of the same category is smaller than the distance between features of different categories. Furthermore, we explore the relationship between the discrimination metric and the discriminability of the original features. Experimental results confirm the effectiveness of the proposed discrimination metric and reveal there exists a trade-off between the discrimination metric and the discriminability of the original features.