Parsing-based View-aware Embedding Network for Vehicle Re-Identification
This work solves vehicle re-identification for surveillance and security applications, representing an incremental advance by refining view-aware feature alignment and enhancement.
The paper tackles vehicle re-identification by addressing large intra-instance distances from different views and subtle inter-instance discrepancies among similar vehicles, proposing a parsing-based view-aware embedding network (PVEN) that achieves state-of-the-art performance with significant improvements on three datasets.
Vehicle Re-Identification is to find images of the same vehicle from various views in the cross-camera scenario. The main challenges of this task are the large intra-instance distance caused by different views and the subtle inter-instance discrepancy caused by similar vehicles. In this paper, we propose a parsing-based view-aware embedding network (PVEN) to achieve the view-aware feature alignment and enhancement for vehicle ReID. First, we introduce a parsing network to parse a vehicle into four different views, and then align the features by mask average pooling. Such alignment provides a fine-grained representation of the vehicle. Second, in order to enhance the view-aware features, we design a common-visible attention to focus on the common visible views, which not only shortens the distance among intra-instances, but also enlarges the discrepancy of inter-instances. The PVEN helps capture the stable discriminative information of vehicle under different views. The experiments conducted on three datasets show that our model outperforms state-of-the-art methods by a large margin.