Context-Aware Graph Convolution Network for Target Re-identification
This work provides an incremental improvement for re-identification systems by better handling hard samples through contextual graph reasoning.
This paper addresses the challenge of re-identifying targets by leveraging context information, specifically probe-gallery and gallery-gallery relationships. The proposed Context-Aware Graph Convolution Network (CAGCN) effectively uses these relationships to improve performance on hard samples, achieving state-of-the-art results on both person and vehicle re-identification datasets.
Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks. However, many of them consider content similarity separately and fail to utilize the context information of the query and gallery sets, e.g. probe-gallery and gallery-gallery relations, thus hard samples may not be well solved due to the limited or even misleading information. In this paper, we present a novel Context-Aware Graph Convolution Network (CAGCN), where the probe-gallery relations are encoded into the graph nodes and the graph edge connections are well controlled by the gallery-gallery relations. In this way, hard samples can be addressed with the context information flows among other easy samples during the graph reasoning. Specifically, we adopt an effective hard gallery sampler to obtain high recall for positive samples while keeping a reasonable graph size, which can also weaken the imbalanced problem in training process with low computation complexity.Experiments show that the proposed method achieves state-of-the-art performance on both person and vehicle re-identification datasets in a plug and play fashion with limited overhead.