A Dual-Path Model With Adaptive Attention For Vehicle Re-Identification

Khorramshahi, Pirazh; Amit, K Roy-Chowdhury; Peri, Neehar; Saketh, Rambhatla Sai; Chen, Jun-Cheng; Chellappa, Rama

doi:10.48550/arxiv.1905.03397

Cited by 8 publications

(16 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(10) AAVER [12], (11) HV-EALN [45]. The proposed methods shows a larger accuracy improvement when com-pared with traditional methods, such as LOMO [40] and DGD [41].…”

Section: Comparison On Vehicleidmentioning

confidence: 97%

“…The results of the proposed method is compared with state-of-the-art methods on VeRi-776 dataset in Tables 1 2, which includes: (1) LOMO [40]; (2) DGD [41]; (3) GoogLeNet [42] (4) PROVID [37]; (5) PathLSTM [43]; (6) OIFE+ST [29]; (7) GSTE [32]; (8) VAMI [27]; (9) VAMI+ST [27]; (10) RAM [20]; (11) AAVER [12]; (12) Part-Regular [13]. The performance comparisons on VeRi-776 dataset have been listed in the Table 1.…”

Section: Evaluation On Veri-776mentioning

confidence: 99%

“…AAVER [12]. Compared with these methods, our method focus on learning details features only from the identity information, which also have significant improvements on VeRi-776.…”

Section: Evaluation On Veri-776mentioning

confidence: 99%

“…Therefore, many reidentification(re-ID) methods [9,10,11] tend to extract vehicle global features that describe the appearance of the vehicle, which supports the same vehicle from various cameras to obtain the correct match. Despite the impressive achievement of deep learning to extract globe features in the re-ID community [12,13,14], learning a re-ID model that focuses on distinguishing local details of vehicles remains a challenge. Variations in local regions of vehicles are difficult to obtain by learning global features.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Discriminative Feature and Dictionary Learning with Part-aware Model for Vehicle Re-identification

Wang

Peng

Jiang

et al. 2020

Preprint

View full text Add to dashboard Cite

With the development of smart cities, urban surveillance video analysis will play a further significant role in intelligent transportation systems. Identifying the same target vehicle in large datasets from non-overlapping cameras should be highlighted, which has grown into a hot topic in promoting intelligent transportation systems. However, vehicle re-identification (re-ID) technology is a challenging task since vehicles of the same design or manufacturer show similar appearance. To fill these gaps, we tackle this challenge by proposing Triplet Center Loss based Part-aware Model (TCPM) that leverages the discriminative features in part details of vehicles to refine the accuracy of vehicle re-identification.TCPM base on part discovery is that partitions the vehicle from horizontal and vertical directions to strengthen the details of the vehicle and reinforce the internal consistency of the parts. In addition, to eliminate intra-class differences in local regions of the vehicle, we propose external memory modules to emphasize the consistency of each part to learn the discriminating features, which forms a global dictionary over all categories in dataset. In TCPM, triplet-center loss is introduced to ensure each part of vehicle features extracted has intra-class consistency and inter-class separability. Experimental results show that our proposed TCPM has an enormous preference over the existing state-of-the-art methods on benchmark datasets VehicleID and VeRi-776.

show abstract

“…(10) AAVER [12], (11) HV-EALN [45]. The proposed methods shows a larger accuracy improvement when com-pared with traditional methods, such as LOMO [40] and DGD [41].…”

Section: Comparison On Vehicleidmentioning

confidence: 97%

Section: Evaluation On Veri-776mentioning

confidence: 99%

“…AAVER [12]. Compared with these methods, our method focus on learning details features only from the identity information, which also have significant improvements on VeRi-776.…”

Section: Evaluation On Veri-776mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Discriminative Feature and Dictionary Learning with Part-aware Model for Vehicle Re-identification

Wang

Peng

Jiang

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Despite recent progress in vehicle reID, in particular deep learning models have made some progress [7], [8], [9], [10], it still suffers from lots of difficulties caused by various viewpoints of vehicles, complicated environments and diversified illuminations, which makes a great difference in the visual appearance of vehicles. Different from other vision tasks [11], [12] , such as person ReID [13], [14], [15], [16] and fine-grained [17], [18], [19], [20], that can extract rich features from images with various poses and colors, vehicles usually have a few attributes that could be utilized to help extract distinctive features for similar vehicles.…”

Section: Introductionmentioning

confidence: 99%

Attribute-guided Feature Learning Network for Vehicle Re-identification

Wang¹,

Peng²,

Chen³

et al. 2020

Preprint

View full text Add to dashboard Cite

Vehicle re-identification (reID) plays an important role in the automatic analysis of the increasing urban surveillance videos, which has become a hot topic in recent years. However, it poses the critical but challenging problem that is caused by various viewpoints of vehicles, diversified illuminations and complicated environments. Till now, most existing vehicle reID approaches focus on learning metrics or ensemble to derive better representation, which are only take identity labels of vehicle into consideration. However, the attributes of vehicle that contain detailed descriptions are beneficial for training reID model. Hence, this paper proposes a novel Attribute-Guided Network (AGNet), which could learn global representation with the abundant attribute features in an end-to-end manner. Specially, an attributeguided module is proposed in AGNet to generate the attribute mask which could inversely guide to select discriminative features for category classification. Besides that, in our proposed AGNet, an attribute-based label smoothing (ALS) loss is presented to better train the reID model, which can strength the distinct ability of vehicle reID model to regularize AGNet model according to the attributes. Comprehensive experimental results clearly demonstrate that our method achieves excellent performance on both VehicleID dataset and VeRi-776 dataset.

show abstract

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

Qian

Jiang

Luo

et al. 2020

Meas. Sci. Technol.

View full text Add to dashboard Cite

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.

show abstract

A Dual-Path Model With Adaptive Attention For Vehicle Re-Identification

Cited by 8 publications

References 0 publications

Discriminative Feature and Dictionary Learning with Part-aware Model for Vehicle Re-identification

Discriminative Feature and Dictionary Learning with Part-aware Model for Vehicle Re-identification

Attribute-guided Feature Learning Network for Vehicle Re-identification

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

Contact Info

Product

Resources

About