Abstract
Object Re-Identification (Re-ID) aims to identify and retrieve specific objects from images captured at different places and times. Recently, object Re-ID has achieved great success with the advances of Vision Transformers (ViT). However, the effects of the global-local relation have not been fully explored in Transformers for object Re-ID. In this work, we first explore the influence of global and local features of ViT and then further propose a novel Global-Local Transformer (GLTrans) for high-performance object Re-ID. We find that the features from last few layers of ViT already have a strong representational ability, and the global and local information can mutually enhance each other. Based on this fact, we propose a Global Aggregation Encoder (GAE) to utilize the class tokens of the last few Transformer layers and learn comprehensive global features effectively. Meanwhile, we propose the Local Multi-layer Fusion (LMF) which leverages both the global cues from GAE and multi-layer patch tokens to explore the discriminative local representations. Extensive experiments demonstrate that our proposed method achieves superior performance on four object Re-ID benchmarks.
Abstract (translated)
物体识别(Re-ID)的目的是从不同时间和地点捕获的图像中识别和检索特定的物体。近年来，随着Vision Transformers (ViT)的进步，物体Re-ID已经取得了巨大的成功。然而，在Transformers中，对全局和局部关系的影响还没有完全被探索。在这项工作中，我们首先探索ViT的局部和全局特征对物体Re-ID的影响，然后进一步提出了一种名为全局-局部Transformer（GLTrans）的高性能物体Re-ID模型。我们发现，ViT最后几层的特征已经具有很强的表示能力，全局和局部信息可以相互增强。基于这个事实，我们提出了一种全局聚合编码器（GAE）来有效地利用最后几个Transformer层中的分类标签，并学习全面的全局特征。同时，我们还提出了一种局部多层融合（LMF），它利用来自GAE的全局线索和多层补丁token来探索具有区分性的局部表示。大量实验证明，我们提出的方法在四个物体Re-ID基准测试中实现了卓越的性能。
URL
https://arxiv.org/abs/2404.14985
