Feature aggregation and connectivity for object re-identification

Dongchen Han, Baodi Liu, Shuai Shao, Weifeng Liu, Yicong Zhou

Abstract: Highlights•We propose a novel framework containing two learnable GCN components.•Our framework can be inserted into arbitrary deep neural networks.•We formulate a new sampling strategy RPGS.•We improve the state-of-the-art methods on both person and vehicle ReID datasets.