Moving Towards Centers: Re-ranking With Attention And Memory For Re-identification

Abstract

Re-ranking utilizes contextual information to optimize the initial ranking list of person or vehicle re-identification (re-ID), which boosts the retrieval performance at post-processing steps. This paper proposes a re-ranking network to predict the correlations between the probe and top-ranked neighbor samples. Specifically, all the feature embeddings of query and gallery images are expanded and enhanced by a linear combination of their neighbors, with the correlation prediction serving as discriminative combination weights. The combination process is equivalent to moving independent embeddings toward the identity centers, improving cluster compactness. For correlation prediction, we first aggregate the contextual information for probe's k-nearest neighbors via the Transformer encoder. Then, we distill and refine the probe-related features into the Contextual Memory cell via attention mechanism. Like humans that retrieve images by not only considering probe images but also memorizing t

Stats

• citations11
• S2 citations—
• github stars0
• HF likes0
• heat score8.09
• arxiv keyzhou2021moving

Related papers

• Re-ranking Person Re-identification With K-reciprocal Encoding (2017)23.09
• Contextual Similarity Aggregation With Self-attention For Visual Re-ranking (2021)0.00
• Adaptive Re-ranking Of Deep Feature For Person Re-identification (2018)0.00
• A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking (2017)23.25
• Neighbor-based Feature And Index Enhancement For Person Re-identification (2025)0.00
• Graph Convolution Based Efficient Re-ranking For Visual Retrieval (2023)9.92
• Graph Convolution For Re-ranking In Person Re-identification (2021)8.35
• Deep Co-attention Based Comparators For Relative Representation Learning In Person Re-identification (2018)13.34