Group-Sensitive Triplet Embedding for Vehicle Reidentification

Bai, Yan; Lou, Yihang; Gao, Feng; Wang, Shiqi; Wu, Yuwei; Duan, Ling-Yu

doi:10.1109/tmm.2018.2796240

Cited by 241 publications

(153 citation statements)

References 49 publications

Supporting

Mentioning

150

Contrasting

Unclassified

Order By: Relevance

“…The softmax output is supervised by the ID label of the training images through the cross-entropy loss. Employing extra crossentropy loss slightly improves the re-ID accuracy of both VANet and the baseline, which is consistent with [1,35].…”

Section: Datasets and Settingssupporting

confidence: 78%

“…Deep metric learning. Deep metric learning is a common approach employed in computer vision tasks e.g., image retrieval [22,34], person and vehicle re-identification [1,3,6] and face recognition [25]. Generally, deep metric learning aims to learn a feature space, in which the samples of a same class are close to each other and the samples of different classes are far away.…”

Section: Related Workmentioning

confidence: 99%

“…Following these definitions, given three samples x, x + , and x − , where x and x + are from a same class (i.e., same vehicle ID in our work) and x − are from another class, we form a positive pair P + = (x, x + ) and a negative pair P − = (x, x − ). A triplet loss is then defined as follows: (1) where α is a margin enforced between positive and negative pairs. Generally, Eq.…”

Section: Metric Learning Baselinementioning

confidence: 99%

See 2 more Smart Citations

Vehicle Re-Identification With Viewpoint-Aware Metric Learning

Chu

Sun

Li³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

177

114

View full text Add to dashboard Cite

This paper considers vehicle re-identification (re-ID) problem. The extreme viewpoint variation (up to 180 degrees) poses great challenges for existing approaches. Inspired by the behavior in human's recognition process, we propose a novel viewpoint-aware metric learning approach. It learns two metrics for similar viewpoints and different viewpoints in two feature spaces, respectively, giving rise to viewpoint-aware network (VANet). During training, two types of constraints are applied jointly. During inference, viewpoint is firstly estimated and the corresponding metric is used. Experimental results confirm that VANet significantly improves re-ID accuracy, especially when the pair is observed from different viewpoints. Our method establishes the new state-of-the-art on two benchmarks. 12 * Corresponding author 1 R. Chu and Y. Sun share equal contribution. 2 Work done at Megvii Technology.

show abstract

Section: Datasets and Settingssupporting

confidence: 78%

Section: Related Workmentioning

confidence: 99%

Section: Metric Learning Baselinementioning

confidence: 99%

See 1 more Smart Citation

Vehicle Re-Identification With Viewpoint-Aware Metric Learning

Chu

Sun

Li³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

177

114

View full text Add to dashboard Cite

show abstract

“…The key practices include hard triplet mining, pretraining for identity classification, dataset augmentation with difficult examples, sufficiently large image resolution, and state-of-theart base architecture. Triplet mining and ID classification have been already adopted in vehicle Re-ID [13], [14]. Kumar et al [14] demonstrated an extensive evaluation of contrastive and triplet losses during vehicle Re-ID.…”

Section: A Re-identification (Re-id)mentioning

confidence: 99%

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

“…4. Mistakes in state-of-the-art Group Sensitive Triplet Learning [41]; images taken directly from original paper. The first row shows retrievals of sedans for a query of truck.…”

Section: B Teamed Classifiers For Vehicle Re-idmentioning

confidence: 99%

Robust, Extensible, and Fast: Teamed Classifiers for Vehicle Tracking in Multi-Camera Networks

Suprem

Lima

Padilha

et al. 2019

2019 IEEE First International Conference on Cognitive Machine Intelligence (CogMI)

View full text Add to dashboard Cite

As camera networks have become more ubiquitous over the past decade, the research interest in video management has shifted to analytics on multi-camera networks. This includes performing tasks such as object detection, attribute identification, and vehicle/person tracking across different cameras without overlap. Current frameworks for management are designed for multi-camera networks in a closed dataset environment where there is limited variability in cameras and characteristics of the surveillance environment are well known. Furthermore, current frameworks are designed for offline analytics with guidance from human operators for forensic applications. This paper presents a teamed classifier framework for video analytics in heterogeneous many-camera networks with adversarial conditions such as multi-scale, multi-resolution cameras capturing the environment with varying occlusion, blur, and orientations. We describe an implementation for vehicle tracking and vehicle re-identification (re-id), where we implement a zero-shot learning (ZSL) system that performs automated tracking of all vehicles all the time. Our evaluations on VeRi-776 and Cars196 show the teamed classifier framework is robust to adversarial conditions, extensible to changing video characteristics such as new vehicle types/brands and new cameras, and offers real-time performance compared to current offline video analytics approaches.

show abstract

Group-Sensitive Triplet Embedding for Vehicle Reidentification

Cited by 241 publications

References 49 publications

Vehicle Re-Identification With Viewpoint-Aware Metric Learning

Vehicle Re-Identification With Viewpoint-Aware Metric Learning

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

Robust, Extensible, and Fast: Teamed Classifiers for Vehicle Tracking in Multi-Camera Networks

Contact Info

Product

Resources

About