CORE-ReID V2 通过优化训练与集成融合，提升跨域目标重识别性能。
CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion
- 用CycleGAN生成多样化数据，缓解不同域间图像特征差异。
- 引入ECAB与SECAB模块，提升特征表示并降低伪标签歧义。
- 支持轻量级网络，在多个数据集上达到最佳mAP和Rank-k准确率。
本文提出CORE-ReID V2，一种增强的无监督域自适应框架，用于行人与车辆重识别，并拓展至通用目标重识别。预训练阶段采用CycleGAN合成多样数据，弥合不同域间的图像特征差距。微调阶段设计先进集成融合机制，结合高效通道注意力块（ECAB）与简化高效通道注意力块（SECAB），增强局部与全局特征表示，同时减少目标域样本伪标签的歧义性。在常用无监督域自适应行人与车辆重识别数据集上的实验表明，该框架优于现有最先进方法，实现最高的均平均精度（mAP）及排名准确率（Top-1、Top-5、Top-10）。此外，框架支持ResNet18与ResNet34等轻量级主干网络，兼顾可扩展性与效率。本工作不仅推动了基于域自适应的目标重识别边界，也为后续研究提供了坚实基础。代码与模型开源：https://github.com/TrinhQuocNguyen/CORE-ReID-V2。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。