Learning View-Specific Deep Networks for Person Re-Identification
This work addresses the challenge of matching pedestrians across disjoint camera views, which is crucial for surveillance and security applications, representing an incremental advancement in deep learning methods for re-identification.
The paper tackles the problem of person re-identification by addressing intra-class variations from changing viewpoints, proposing a deep neural network framework that learns view-specific networks with cross-view constraints, resulting in significant performance improvements and outperforming state-of-the-art methods on multiple benchmarks.
In recent years, a growing body of research has focused on the problem of person re-identification (re-id). The re-id techniques attempt to match the images of pedestrians from disjoint non-overlapping camera views. A major challenge of re-id is the serious intra-class variations caused by changing viewpoints. To overcome this challenge, we propose a deep neural network-based framework which utilizes the view information in the feature extraction stage. The proposed framework learns a view-specific network for each camera view with a cross-view Euclidean constraint (CV-EC) and a cross-view center loss (CV-CL). We utilize CV-EC to decrease the margin of the features between diverse views and extend the center loss metric to a view-specific version to better adapt the re-id problem. Moreover, we propose an iterative algorithm to optimize the parameters of the view-specific networks from coarse to fine. The experiments demonstrate that our approach significantly improves the performance of the existing deep networks and outperforms the state-of-the-art methods on the VIPeR, CUHK01, CUHK03, SYSU-mReId, and Market-1501 benchmarks.