Virtual CNN Branching: Efficient Feature Ensemble for Person Re-Identification
This is an incremental improvement for person re-identification, addressing misalignment and variations in viewing angles with minimal added cost.
The paper tackles the problem of person re-identification by introducing a virtual branching ensemble method for CNNs that specializes neurons in different aspects like body regions or poses, achieving competitive performance on benchmarks such as Market-1501, CUHK03, and DukeMTMC-reID.
In this paper we introduce an ensemble method for convolutional neural network (CNN), called "virtual branching," which can be implemented with nearly no additional parameters and computation on top of standard CNNs. We propose our method in the context of person re-identification (re-ID). Our CNN model consists of shared bottom layers, followed by "virtual" branches, where neurons from a block of regular convolutional and fully-connected layers are partitioned into multiple sets. Each virtual branch is trained with different data to specialize in different aspects, e.g., a specific body region or pose orientation. In this way, robust ensemble representations are obtained against human body misalignment, deformations, or variations in viewing angles, at nearly no any additional cost. The proposed method achieves competitive performance on multiple person re-ID benchmark datasets, including Market-1501, CUHK03, and DukeMTMC-reID.