Person Re-identification With Deep Similarity-guided Graph Neural Network

Abstract

The person re-identification task requires to robustly estimate visual similarities between person images. However, existing person re-identification models mostly estimate the similarities of different image pairs of probe and gallery images independently while ignores the relationship information between different probe-gallery pairs. As a result, the similarity estimation of some hard samples might not be accurate. In this paper, we propose a novel deep learning framework, named Similarity-Guided Graph Neural Network (SGGNN) to overcome such limitations. Given a probe image and several gallery images, SGGNN creates a graph to represent the pairwise relationships between probe-gallery pairs (nodes) and utilizes such relationships to update the probe-gallery relation features in an end-to-end manner. Accurate similarity estimation can be achieved by using such updated probe-gallery relation features for prediction. The input features for nodes on the graph are the relation features of

Stats

• citations218
• S2 citations—
• github stars0
• HF likes0
• heat score17.55
• arxiv keyshen2018person

Related papers

• Pgganet: Pose Guided Graph Attention Network For Person Re-identification (2021)0.00
• Graph Convolution For Re-ranking In Person Re-identification (2021)8.35
• Deep Group-shuffling Random Walk For Person Re-identification (2018)15.48
• Triplet-based Deep Similarity Learning For Person Re-identification (2018)10.61
• Deep Constrained Dominant Sets For Person Re-identification (2019)9.23
• Multi-granularity Graph Pooling For Video-based Person Re-identification (2022)12.17
• Pose-aided Video-based Person Re-identification Via Recurrent Graph Convolutional Network (2022)10.97
• Large Margin Learning In Set To Set Similarity Comparison For Person Re-identification (2017)12.10