Multi-Domain Joint Training for Person Re-Identification

TL;DR

This paper introduces a dynamic network model that adapts to diverse environments, enabling better utilization of multiple datasets for person re-identification and significantly improving performance.

Contribution

The paper proposes the Domain-Camera-Sample Dynamic network (DCSD), an adaptive model that improves multi-dataset training for person ReID by accounting for domain and camera variations.

Findings

DCSD boosts ReID performance by up to 12.3%.

Training with adaptive models benefits from more diverse data.

Standard models may perform worse with combined datasets.

Abstract

Deep learning-based person Re-IDentification (ReID) often requires a large amount of training data to achieve good performance. Thus it appears that collecting more training data from diverse environments tends to improve the ReID performance. This paper re-examines this common belief and makes a somehow surprising observation: using more samples, i.e., training with samples from multiple datasets, does not necessarily lead to better performance by using the popular ReID models. In some cases, training with more samples may even hurt the performance of the evaluation is carried out in one of those datasets. We postulate that this phenomenon is due to the incapability of the standard network in adapting to diverse environments. To overcome this issue, we propose an approach called Domain-Camera-Sample Dynamic network (DCSD) whose parameters can be adaptive to various factors. Specifically, we consider the internal domain-related factor that can be identified from the input features, and external domain-related factors, such as domain information or camera information. Our discovery is that training with such an adaptive model can better benefit from more training samples. Experimental results show that our DCSD can greatly boost the performance (up to 12.3%) while joint training in multiple datasets.