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 this https URL.
Abstract (translated)
这项研究提出了CORE-ReID V2，这是一个在原有的CORE-ReID基础上增强的框架。新框架通过解决人再识别（Person ReID）和车辆再识别（Vehicle ReID）中的无监督领域适应（UDA）挑战，并进一步扩展到物体再识别（Object ReID），来改进其前身。在预训练阶段，CycleGAN被用来合成多样化的数据集，以弥合不同域之间图像特征的差距。在微调阶段，一个先进的集成融合机制由高效的通道注意力块（ECAB）和简化的高效通道注意力块（SECAB）组成，提高了局部和全局特征表示能力，并减少了目标样本伪标签中的不确定性。 实验结果表明，在广泛使用的UDA Person ReID和Vehicle ReID数据集上，所提出的框架超越了最先进的方法，在平均精度均值（mAP）和等级准确度（Top-1、Top-5、Top-10）方面取得了最佳性能。此外，该框架支持轻量级的骨干网络如ResNet18和ResNet34，确保了可扩展性和高效性。 我们的工作不仅推动了基于UDA的物体再识别领域的边界，并且为后续的研究和发展奠定了坚实的基础。我们提供的代码和模型可在以下网址获得：[此URL]。
URL
https://arxiv.org/abs/2508.04036
