Graph Convolution For Re-ranking In Person Re-identification

Abstract

Nowadays, deep learning is widely applied to extract features for similarity computation in person re-identification (re-ID) and have achieved great success. However, due to the non-overlapping between training and testing IDs, the difference between the data used for model training and the testing data makes the performance of learned feature degraded during testing. Hence, re-ranking is proposed to mitigate this issue and various algorithms have been developed. However, most of existing re-ranking methods focus on replacing the Euclidean distance with sophisticated distance metrics, which are not friendly to downstream tasks and hard to be used for fast retrieval of massive data in real applications. In this work, we propose a graph-based re-ranking method to improve learned features while still keeping Euclidean distance as the similarity metric. Inspired by graph convolution networks, we develop an operator to propagate features over an appropriate graph. Since graph is the essenti

Stats

• citations12
• S2 citations—
• github stars0
• HF likes0
• heat score8.35
• arxiv keyzhang2021graph

Related papers

• Graph Convolution Based Efficient Re-ranking For Visual Retrieval (2023)9.92
• Adaptive Re-ranking Of Deep Feature For Person Re-identification (2018)0.00
• Re-ranking Person Re-identification With K-reciprocal Encoding (2017)23.09
• Ranking And Classification Driven Feature Learning For Person Re_identification (2019)4.01
• Understanding Image Retrieval Re-ranking: A Graph Neural Network Perspective (2020)0.00
• Person Re-identification With Deep Similarity-guided Graph Neural Network (2018)17.55
• Multi-granularity Graph Pooling For Video-based Person Re-identification (2022)12.17
• Ensemble Feature For Person Re-identification (2019)0.00