Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification
This work addresses the need for more efficient and effective models in person re-identification, an incremental improvement over existing methods by automating architecture design for this specific domain.
The authors tackled the problem of designing efficient CNN architectures for person re-identification by proposing Auto-ReID, a neural architecture search method that incorporates body structural information and retrieval-based optimization, resulting in state-of-the-art performance with a 50% reduction in parameters and 53% reduction in FLOPs.
Prevailing deep convolutional neural networks (CNNs) for person re-IDentification (reID) are usually built upon ResNet or VGG backbones, which were originally designed for classification. Because reID is different from classification, the architecture should be modified accordingly. We propose to automatically search for a CNN architecture that is specifically suitable for the reID task. There are three aspects to be tackled. First, body structural information plays an important role in reID but it is not encoded in backbones. Second, Neural Architecture Search (NAS) automates the process of architecture design without human effort, but no existing NAS methods incorporate the structure information of input images. Third, reID is essentially a retrieval task but current NAS algorithms are merely designed for classification. To solve these problems, we propose a retrieval-based search algorithm over a specifically designed reID search space, named Auto-ReID. Our Auto-ReID enables the automated approach to find an efficient and effective CNN architecture for reID. Extensive experiments demonstrate that the searched architecture achieves state-of-the-art performance while reducing 50% parameters and 53% FLOPs compared to others.