Context-Aware Graph Convolution Network for Target Re-identification

TL;DR

This paper introduces a novel Context-Aware Graph Convolution Network (CAGCN) for re-identification tasks that leverages context information among samples to improve accuracy, especially on hard samples, achieving state-of-the-art results.

Contribution

The paper proposes a new graph-based model that encodes probe-gallery and gallery-gallery relations to enhance re-identification performance, addressing hard samples and class imbalance.

Findings

Achieves state-of-the-art performance on person and vehicle re-identification datasets.

Effectively handles hard samples through context information flow in the graph.

Maintains low computational overhead with a novel sampling strategy.

Abstract

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.