Center Prediction Loss for Re-identification

TL;DR

This paper introduces Center Prediction Loss (CPL), a novel training loss for re-identification systems that balances intra-class distribution flexibility and inter-class separation, leading to improved performance.

Contribution

The paper proposes a new loss function, CPL, which predicts class centers from individual samples, offering a more flexible intra-class constraint without extra hyper-parameters.

Findings

CPL achieves superior performance on ReID datasets.

CPL complements existing loss functions effectively.

It maintains class separation while allowing intra-class distribution flexibility.

Abstract

The training loss function that enforces certain training sample distribution patterns plays a critical role in building a re-identification (ReID) system. Besides the basic requirement of discrimination, i.e., the features corresponding to different identities should not be mixed, additional intra-class distribution constraints, such as features from the same identities should be close to their centers, have been adopted to construct losses. Despite the advances of various new loss functions, it is still challenging to strike the balance between the need of reducing the intra-class variation and allowing certain distribution freedom. In this paper, we propose a new loss based on center predictivity, that is, a sample must be positioned in a location of the feature space such that from it we can roughly predict the location of the center of same-class samples. The prediction error is then regarded as a loss called Center Prediction Loss (CPL). We show that, without introducing additional hyper-parameters, this new loss leads to a more flexible intra-class distribution constraint while ensuring the between-class samples are well-separated. Extensive experiments on various real-world ReID datasets show that the proposed loss can achieve superior performance and can also be complementary to existing losses.