Divide and Fuse: A Re-ranking Approach for Person Re-identification
arXiv:1708.04169
Abstract
As re-ranking is a necessary procedure to boost person re-identification (re-ID) performance on large-scale datasets, the diversity of feature becomes crucial to person reID for its importance both on designing pedestrian descriptions and re-ranking based on feature fusion. However, in many circumstances, only one type of pedestrian feature is available. In this paper, we propose a "Divide and use" re-ranking framework for person re-ID. It exploits the diversity from different parts of a high-dimensional feature vector for fusion-based re-ranking, while no other features are accessible. Specifically, given an image, the extracted feature is divided into sub-features. Then the contextual information of each sub-feature is iteratively encoded into a new feature. Finally, the new features from the same image are fused into one vector for re-ranking. Experimental results on two person re-ID benchmarks demonstrate the effectiveness of the proposed framework. Especially, our method outperforms the state-of-the-art on the Market-1501 dataset.
arXiv commentAccepted by BMVC2017
References in corpus (1)
Cited by in corpus (5)
- The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching
- Towards Good Practices on Building Effective CNN Baseline Model for Person Re-identification
- Adaptively Connected Neural Networks
- Push for Center Learning via Orthogonalization and Subspace Masking for Person Re-Identification
- Cross-Resolution Person Re-identification with Deep Antithetical Learning