CVLGNov 21, 2018

Adaptive Re-ranking of Deep Feature for Person Re-identification

arXiv:1811.08561v11 citations
Originality Incremental advance
AI Analysis

This addresses person re-identification for surveillance and security applications, representing an incremental improvement over existing methods.

The paper tackles person re-identification by proposing a Deep Feature Fusion method to exploit diverse information in deep features and an Adaptive Re-Ranking method to use contextual neighbor information, achieving superior performance on three large benchmarks.

Typical person re-identification (re-ID) methods train a deep CNN to extract deep features and combine them with a distance metric for the final evaluation. In this work, we focus on exploiting the full information encoded in the deep feature to boost the re-ID performance. First, we propose a Deep Feature Fusion (DFF) method to exploit the diverse information embedded in a deep feature. DFF treats each sub-feature as an information carrier and employs a diffusion process to exchange their information. Second, we propose an Adaptive Re-Ranking (ARR) method to exploit the contextual information encoded in the features of neighbors. ARR utilizes the contextual information to re-rank the retrieval results in an iterative manner. Particularly, it adds more contextual information after each iteration automatically to consider more matches. Third, we propose a strategy that combines DFF and ARR to enhance the performance. Extensive comparative evaluations demonstrate the superiority of the proposed methods on three large benchmarks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes