Heterogeneous Relational Complement for Vehicle Re-identification
This work addresses the problem of accurately identifying vehicles across different camera views for applications like surveillance and traffic monitoring, representing an incremental improvement with novel components.
The paper tackles vehicle re-identification by proposing a Heterogeneous Relational Complement Network (HRCN) to learn viewpoint-invariant representations and a Cross-camera Generalization Measure (CGM) for improved evaluation, achieving state-of-the-art results on VeRi-776, VehicleID, and VERI-Wild benchmarks.
The crucial problem in vehicle re-identification is to find the same vehicle identity when reviewing this object from cross-view cameras, which sets a higher demand for learning viewpoint-invariant representations. In this paper, we propose to solve this problem from two aspects: constructing robust feature representations and proposing camera-sensitive evaluations. We first propose a novel Heterogeneous Relational Complement Network (HRCN) by incorporating region-specific features and cross-level features as complements for the original high-level output. Considering the distributional differences and semantic misalignment, we propose graph-based relation modules to embed these heterogeneous features into one unified high-dimensional space. On the other hand, considering the deficiencies of cross-camera evaluations in existing measures (i.e., CMC and AP), we then propose a Cross-camera Generalization Measure (CGM) to improve the evaluations by introducing position-sensitivity and cross-camera generalization penalties. We further construct a new benchmark of existing models with our proposed CGM and experimental results reveal that our proposed HRCN model achieves new state-of-the-art in VeRi-776, VehicleID, and VERI-Wild.