Stripe-based and attribute-aware network: a two-branch deep model for vehicle re-identification

Abstract

Vehicle re-identification (Re-ID) has been attracting increasing interest in the field of computer vision due to the growing utilization of surveillance cameras in public security. However, vehicle Re-ID still suffers a similarity challenge despite the efforts made to solve this problem. This challenge involves distinguishing different instances with nearly identical appearances. In this paper, we propose a novel two-branch stripebased and attribute-aware deep convolutional neural network (SAN) to learn the efficient feature embedding for vehicle Re-ID task. The two-branch neural network, consisting of stripe-based branch and attribute-aware branches, can adaptively extract the discriminative features from the visual appearance of vehicles. A horizontal average pooling and dimension-reduced convolutional layers are inserted into the stripe-based branch to achieve partlevel features. Meanwhile, the attribute-aware branch extracts the global feature under the supervision of vehicle attribute labels to separate the similar vehicle identities with different attribute annotations. Finally, the part-level and global features are concatenated together to form the final descriptor of the input image for vehicle Re-ID. The final descriptor not only can separate vehicles with different attributes but also distinguish vehicle identities with the same attributes. The extensive experiments on both VehicleID and VeRi databases show that the proposed SAN method outperforms other state-of-the-art vehicle Re-ID approaches.

Pseudo Graph Convolutional Network for Vehicle ReID

“…2) Compared to the part-based and attribute-based methods [11,29,32,53], PGVR achieves significant improvement, e.g. up to 3.5% mAP on VeRi-776, 3.3% mAP on VehicleID, and 2.1% mAP on VERI-WILD, which validates that the student in PGVR can learn better fine-grained information than these methods.…”

“…-based approaches: PGAN [51], PRN [11], PVEN [29], and GLAMOR [39]; (2) attribute-based approaches: AGNet-ASL [42], DJDL [24], XG-6-sub-multi [53], and SAN [32]; (3) attention-based approaches: AAVER [18] and SEVER [19]; (4) other interesting approaches: GSTE [1], VAMI [56], and DCDLearn [59].…”

Revisiting the CompCars Dataset for Hierarchical Car Classification: New Annotations, Experiments, and Results

“…Partially related to the task of car classification, vehicle re-identification consists of recognizing a specific instance across a set of alternatives with similar appearance, when license plate recognition is not reliable or not available. To this extent, in 2020, Qian et al [ 25 ] developed an attribute-aware re-identification network that exploits information relative to the car model and type to build a rich and effective feature representation. Given the different nature of the problem, they focus on re-identification datasets VehicleID [ 26 ] and VeRi [ 27 ], while the CompCars dataset is only used as pretraining set for a baseline based on the GoogLeNet architecture [ 28 ].…”

High Confidence Attribute Recognition For Vehicle Re-Identification

“…Moreover, the method including both two attribute models achieves higher Top-1 accuracy. [11] 0.611 0.562 0.514 AAVER [21] 0.747 0.686 0.635 RAM [20] 0.752 0.723 0.677 Part-regularized [18] 0.784 0.750 0.742 SAN [23] 0.797 0.784 0.756 SAVER [22] 0.799 0.776 0.753 HCANet 0.837 0.811 0.780…”