Graph-based models have achieved great success in person re-identification tasks recently, which compute the graph topology structure (affinities) among different people first and then pass the information across them to achieve stronger features. But we find existing graph-based methods in the visible-infrared person re-identification task (VI-ReID) suffer from bad generalization because of two issues: 1) train-test modality balance gap, which is a property of VI-ReID task. The number of two modalities data are balanced in the training stage, but extremely unbalanced in inference, causing the low generalization of graph-based VI-ReID methods. 2) sub-optimal topology structure caused by the end-to-end learning manner to the graph module. We analyze that the well-trained input features weaken the learning of graph topology, making it not generalized enough during the inference process. In this paper, we propose a Counterfactual Intervention Feature Transfer (CIFT) method to tackle these problems. Specifically, a Homogeneous and Heterogeneous Feature Transfer (H2FT) is designed to reduce the train-test modality balance gap by two independent types of well-designed graph modules and an unbalanced scenario simulation. Besides, a Counterfactual Relation Intervention (CRI) is proposed to utilize the counterfactual intervention and causal effect tools to highlight the role of topology structure in the whole training process, which makes the graph topology structure more reliable. Extensive experiments on standard VI-ReID benchmarks demonstrate that CIFT outperforms the state-of-the-art methods under various settings.
翻译:最近,基于图表的模型在个人再识别任务方面取得了巨大的成功,这些模型首先计算不同人群之间的图形表层结构(亲和),然后将信息传递给不同人群,以达到更强的特征。但我们发现,在可见红外人士再识别任务(VI-ReID)中,现有基于图表的方法因以下两个问题而出现失佳的概括化:1)培训测试模式的平衡差距,这是VI-ReID任务的一个属性。两种模式数据的数量在培训阶段是平衡的,但极不平衡的推论,导致基于图形的VI-ReID方法的概括化程度较低。2)由于端到端学习到图模块的模块,我们发现,在可见红外再识别任务(VI-REID)中,现有的基于图表的基于图表的方法存在不完善的基于图表的方法,使图表的学习变得不够普遍化。在本文件中,我们提出了一种反事实干预特征的转移(CIFT)方法,具体地说,一种基于图形的直径直径转换(H2FT)方法,由端到图表学习方式的亚缩缩缩缩缩缩缩图模型结构结构。