Parsing-Based View-Aware Embedding Network for Vehicle Re-Identification

Meng, Dechao; Li, Liang; Liu, Xuejing; Li, Yadong; Yang, Shi-Jie; Zha, Zheng-Jun; Gao, Xingyu; Wang, Shuhui; Huang, Qingming

doi:10.1109/cvpr42600.2020.00713

Cited by 185 publications

(121 citation statements)

References 27 publications

Supporting

Mentioning

121

Contrasting

Order By: Relevance

“…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.…”

Section: Implementation Detailsmentioning

confidence: 57%

“…In [24], researchers intend to train the attribute classification task and the Vehicle Re-ID task simultaneously by a joint learning approach. Finally, viewpoint changes can cause a large variety of intra-class differences in vehicle Re-ID, and many methods are proposed and focus on solving this problem [5,29].…”

Section: Related Work 21 Vehicle Reidmentioning

confidence: 99%

“…-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].…”

Section: Implementation Detailsmentioning

confidence: 99%

See 2 more Smart Citations

Pseudo Graph Convolutional Network for Vehicle ReID

Qian

Peng

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Image-based Vehicle ReID methods have suffered from limited information caused by viewpoints, illumination, and occlusion as they usually use a single image as input. Graph convolutional methods (GCN) can alleviate the aforementioned problem by aggregating neighbor samples' information to enhance the feature representation. However, it's uneconomical and computational for the inference processes of GCN-based methods since they need to iterate over all samples for searching the neighbor nodes. In this paper, we propose the first Pseudo-GCN Vehicle ReID method (PGVR) which enables a CNN-based module to performs competitively to GCN-based methods and has a faster and lightweight inference process. To enable the Pseudo-GCN mechanism, a two-branch network and a graph-based knowledge distillation are proposed. The two-branch network consists of a CNN-based student branch and a GCN-based teacher branch. The GCN-based teacher branch adopts a ReID-based GCN to learn the topological optimization ability under the supervision of ReID tasks during training time. Moreover, the graph-based knowledge distillation explicitly transfers the topological optimization ability from the teacher branch to the student branch which acknowledges all nodes. We evaluate our proposed method PGVR on three mainstream Vehicle ReID benchmarks and demonstrate that PGVR achieves state-of-the-art performance. CCS CONCEPTS• Computing methodologies → Computer vision; Neural networks; • Information systems → Retrieval models and ranking.

show abstract

Section: Implementation Detailsmentioning

confidence: 57%

Section: Related Work 21 Vehicle Reidmentioning

confidence: 99%

See 1 more Smart Citation

Pseudo Graph Convolutional Network for Vehicle ReID

Qian

Peng

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…However, the artificial features depend on human experience to a large extent, and the deep information of image is not easy to be mined, so the effectiveness of artificial features is hard to be ensured. Therefore, the deep learning based vehicle recognition algorithms are paid more attention in recent years, which include some traditional deep learning models such as Convolutional Neural Network model [13][14][15], Deep Belief Network model [16][17], Transfer learning model [18][19][20], Restricted Boltzmann Machine [21][22][23], and some improved models such as Conv5 [24], Teacher-Student Network [25], Parsing-based View-aware Embedding Network [26], Semantics-guided Part Attention Network [27], the model fused by multiple networks [28], and the network based on reconstruction [29], et al For the supervised vehicle classification problem, these deep learning methods have achieved good results, but for vehicle face matching problem under the conditions that the times of each vehicle being captured is very limited and the number of the training samples is too small, the universalities of these models are not very well. Therefore, under a limited number of vehicle face samples, it is very meaningful to propose a vehicle re-identification algorithm with good robustness and universality.…”

Section: Related Workmentioning

confidence: 99%

“…When judging whether two images (26) then, we will measure the similarity of two vehicle face features by using ( 27), if d η > , the two images can be considered to represent the same vehicle, on the contrary, they represent different vehicles, where η is the similarity threshold.…”

Section: Feature Matching Based On Cosine Distancementioning

confidence: 99%

Vehicle Face Re-identification Based on Nonnegative Matrix Factorization with Time Difference Constraint

2021

KSII TIIS

View full text Add to dashboard Cite

Light intensity variation is one of the key factors which affect the accuracy of vehicle face re-identification, so in order to improve the robustness of vehicle face features to light intensity variation, a Nonnegative Matrix Factorization model with the constraint of image acquisition time difference is proposed. First, the original features vectors of all pairs of positive samples which are used for training are placed in two original feature matrices respectively, where the same columns of the two matrices represent the same vehicle; Then, the new features obtained after decomposition are divided into stable and variable features proportionally, where the constraints of intra-class similarity and inter-class difference are imposed on the stable feature, and the constraint of image acquisition time difference is imposed on the variable feature; At last, vehicle face matching is achieved through calculating the cosine distance of stable features. Experimental results show that the average False Reject Rate and the average False Accept Rate of the proposed algorithm can be reduced to 0.14 and 0.11 respectively on five different datasets, and even sometimes under the large difference of light intensities, the vehicle face image can be still recognized accurately, which verifies that the extracted features have good robustness to light variation.

show abstract