Neural Architecture Search (NAS) has been increasingly appealing to the society of object Re-Identification (ReID), for that task-specific architectures significantly improve the retrieval performance. Previous works explore new optimizing targets and search spaces for NAS ReID, yet they neglect the difference of training schemes between image classification and ReID. In this work, we propose a novel Twins Contrastive Mechanism (TCM) to provide more appropriate supervision for ReID architecture search. TCM reduces the category overlaps between the training and validation data, and assists NAS in simulating real-world ReID training schemes. We then design a Multi-Scale Interaction (MSI) search space to search for rational interaction operations between multi-scale features. In addition, we introduce a Spatial Alignment Module (SAM) to further enhance the attention consistency confronted with images from different sources. Under the proposed NAS scheme, a specific architecture is automatically searched, named as MSINet. Extensive experiments demonstrate that our method surpasses state-of-the-art ReID methods on both in-domain and cross-domain scenarios. Source code available in https://github.com/vimar-gu/MSINet.

翻译：神经架构搜索（NAS）在行人重识别（ReID）领域日益受到关注，因为任务特定的架构能显著提升检索性能。以往工作探索了面向NAS ReID的优化目标和搜索空间，但忽略了图像分类与ReID训练策略之间的差异。为此，本文提出一种新颖的孪生对比机制（TCM），为ReID架构搜索提供更合适的监督信号。TCM通过减少训练集与验证集之间的类别重叠，帮助NAS模拟真实世界的ReID训练流程。我们还设计了多尺度交互（MSI）搜索空间，以搜索多尺度特征间合理的交互操作。此外，引入空间对齐模块（SAM）进一步增强面对不同来源图像时的注意力一致性。在该NAS方案下，自动搜索出一种特定架构，命名为MSINet。大量实验表明，我们的方法在域内和跨域场景中均超越了当前最先进的ReID方法。源代码请参见https://github.com/vimar-gu/MSINet。