CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion

TL;DR

CORE-ReID V2 introduces an improved domain adaptation framework for Object ReID, utilizing synthetic data generation and advanced ensemble fusion to enhance feature representation and outperform existing methods.

Contribution

The paper presents a novel framework that extends CORE-ReID by integrating CycleGAN-based data synthesis and a new ensemble fusion mechanism, advancing unsupervised domain adaptation in Object ReID.

Findings

Outperforms state-of-the-art in UDA Person and Vehicle ReID datasets

Supports lightweight backbones like ResNet18 and ResNet34

Achieves top performance in mAP and Rank-k accuracy

Abstract

This study presents CORE-ReID V2, an enhanced framework building upon CORE-ReID. The new framework extends its predecessor by addressing Unsupervised Domain Adaptation (UDA) challenges in Person ReID and Vehicle ReID, with further applicability to Object ReID. During pre-training, CycleGAN is employed to synthesize diverse data, bridging image characteristic gaps across different domains. In the fine-tuning, an advanced ensemble fusion mechanism, consisting of the Efficient Channel Attention Block (ECAB) and the Simplified Efficient Channel Attention Block (SECAB), enhances both local and global feature representations while reducing ambiguity in pseudo-labels for target samples. Experimental results on widely used UDA Person ReID and Vehicle ReID datasets demonstrate that the proposed framework outperforms state-of-the-art methods, achieving top performance in Mean Average Precision (mAP) and Rank-k Accuracy (Top-1, Top-5, Top-10). Moreover, the framework supports lightweight backbones such as ResNet18 and ResNet34, ensuring both scalability and efficiency. Our work not only pushes the boundaries of UDA-based Object ReID but also provides a solid foundation for further research and advancements in this domain. Our codes and models are available at https://github.com/TrinhQuocNguyen/CORE-ReID-V2.