Multi-scale Deep Learning Architectures for Person Re-identification
This addresses the challenge of matching people across surveillance cameras where appearance differences are subtle, offering a domain-specific improvement for computer vision applications.
The paper tackles the problem of person re-identification by proposing a multi-scale deep learning model that learns discriminative features at different scales and automatically selects the best scales for matching, outperforming state-of-the-art methods on multiple benchmarks.
Person Re-identification (re-id) aims to match people across non-overlapping camera views in a public space. It is a challenging problem because many people captured in surveillance videos wear similar clothes. Consequently, the differences in their appearance are often subtle and only detectable at the right location and scales. Existing re-id models, particularly the recently proposed deep learning based ones match people at a single scale. In contrast, in this paper, a novel multi-scale deep learning model is proposed. Our model is able to learn deep discriminative feature representations at different scales and automatically determine the most suitable scales for matching. The importance of different spatial locations for extracting discriminative features is also learned explicitly. Experiments are carried out to demonstrate that the proposed model outperforms the state-of-the art on a number of benchmarks