Vehicle re-identification based on dimensional decoupling strategy and non-local relations.

Vehicle re-identification (Re-ID) is a challenging task that aims to recognize the same vehicle across different non-overlapping cameras. Existing attention mechanism-based methods for vehicle Re-ID often suffer from significant intra-class variation and inter-class variation due to various factors such as illumination, occlusion, viewpoint, etc. In this paper, we propose a novel network architecture for vehicle Re-ID, named Dimensional Decoupling Strategy and Non-local Relationship Network (DMNR-Net), which uses three modules to extract complementary features: global feature extraction module, non-local relationship capture module(NRCM), and dimensional decoupling module (DDS). The global feature extraction module captures complete and coarse-grained features from the whole image; the NRCM module extracts saliency information from feature maps in both spatial and channel dimensions; and the DDS decouples spatial and channel features into two branches to extract fine-grained features and focus on specific subspaces. We conduct extensive experiments on two popular publicly datasets, VeRi-776 and VehicleID, to evaluate the effectiveness of our method. The experimental results show that our DMNR-Net outperforms state-of-the-art methods by a large margin on both datasets.

Heterogeneous context interaction network for vehicle re-identification.

Capturing global and subtle discriminative information using attention mechanisms is essential to address the challenge of inter-class high similarity for vehicle re-identification (Re-ID) task. Mixing self-information of nodes or modeling context based on pairwise dependencies between nodes are the core ideas of current advanced attention mechanisms. This paper aims to explore how to utilize both dependency context and self-context in an efficient way to facilitate attention to learn more effectively. We propose a heterogeneous context interaction (HCI) attention mechanism that infers the weights of nodes from the interactions of global dependency contexts and local self-contexts to enhance the effect of attention learning. To reduce computational complexity, global dependency contexts are modeled by aggregating number-compressed pairwise dependencies, and the interactions of heterogeneous contexts are restricted to a certain range. Based on this mechanism, we propose a heterogeneous context interaction network (HCI-Net), which uses channel heterogeneous context interaction module (CHCI) and spatial heterogeneous context interaction module (SHCI), and introduces a rigid partitioning strategy to extract important global and fine-grained features. In addition, we design a non-similarity constraint (NSC) that forces the HCI-Net to learn diverse subtle discriminative information. The experiment results on two large datasets, VeRi-776 and VehicleID, show that our proposed HCI-Net achieves the state-of-the-art performance. In particular, the mean average precision (mAP) reaches 83.8% on VeRi-776 dataset.

Multi-Receptive Field Soft Attention Part Learning for Vehicle Re-Identification.

Vehicle re-identification across multiple cameras is one of the main problems of intelligent transportation systems (ITSs). Since the differences in the appearance between different vehicles of the same model are small and the appearance of the same vehicle changes drastically from different viewpoints, vehicle re-identification is a challenging task. In this paper, we propose a model called multi-receptive field soft attention part learning (MRF-SAPL). The MRF-SAPL model learns semantically diverse vehicle part-level features under different receptive fields through multiple local branches, alleviating the problem of small differences in vehicle appearance. To align vehicle parts from different images, this study uses soft attention to adaptively locate the positions of the parts on the final feature map generated by a local branch and maintain the continuity of the internal semantics of the parts. In addition, to obtain parts with different semantic patterns, we propose a new loss function that punishes overlapping regions, forcing the positions of different parts on the same feature map to not overlap each other as much as possible. Extensive ablation experiments demonstrate the effectiveness of our part-level feature learning method MRF-SAPL, and our model achieves state-of-the-art performance on two benchmark datasets.