Going Beyond Real Data: A Robust Visual Representation for Vehicle Re-identification

Zheng, Zhedong; Jiang, Minyue; Wang, Zhigang; Wang, Jian; Bai, Zechen; Zhang, Xuanmeng; Yu, Xin; Tan, Xiao; Yang, Yi; Wen, Shifeng; Ding, Errui

doi:10.1109/cvprw50498.2020.00307

Cited by 43 publications

(19 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To relieve the pressure of using large real data sets, VehicleX, 18 a large‐scale virtual vehicle re‐ID data set, was generated for vehicle re‐ID, which has consistent content with the target domain. Then the methods 25–27 all adopt “real combined with virtual” and used the VehicleX for data augmentation in different ways. Identity mining (IM) method 27 was proposed to facilitate multidomain learning based on real and virtual data sets.…”

Section: Related Workmentioning

confidence: 99%

Efficient virtual data search for annotation‐free vehicle reidentification

Wan

Wang

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Vehicle reidentification (re‐ID) is the task of retrieving the same vehicle across nonoverlapping cameras, which has made significant progress with the help of abundant manually annotated real images. To avoid the time‐consuming and tedious labeling of real images, virtual data sets with large‐scale synthetic images have recently been constructed to perform annotation‐free model training. However, current methods fail to exploit the potential of virtual data search, that is, searching valuable and representative virtual subdata set for efficient training. This paper presents a novel data sampling strategy from both semantic and feature levels to perform an effective data search. The semantic level determines the sample number of each vehicle identity via the consistency constraint of attribute distribution for source domain and target domain; while the feature level searches valuable and representative samples of each vehicle identity. To our knowledge, we are among the first attempts to search effective virtual data to perform annotation‐free vehicle re‐ID. Extensive cross‐domain experiments from virtual vehicle re‐ID data sets to real vehicle re‐ID data sets show that our data sampling strategy can significantly reduce the training data volume and even boost the re‐ID performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Efficient virtual data search for annotation‐free vehicle reidentification

Wan

Wang

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

“…A summary of the best performing methods is found in [26]. Noticeable trends from these methods are the extraction of additional attributes [6,39,3] (color, type, orientation), the deployment of state-of-the-art classification networks such as ResNet-IBN [27], and the combination of classification and metric losses [38,31,10].…”

Section: Related Workmentioning

confidence: 99%

“…Meanwhile, the authors of [12] deploy a strong baseline architecture [25] in conjunction with a twostep training process that leverages the availability of synthetic data. The best performing system [38] uses both style transform and content manipulation, to reduce the synthetic-to-real domain gap and enhance the training data. These improvements, together with camera and orientation-aware models, yield excellent performance for vehicle Re-ID.…”

Section: Related Workmentioning

confidence: 99%

TIED: A Cycle Consistent Encoder-Decoder Model for Text-to-Image Retrieval

Sebastian

Imbriaco

Meletis

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Retrieving specific vehicle tracks by Natural Language (NL)-based descriptions is a convenient way to monitor vehicle movement patterns and traffic-related events. NLbased image retrieval has several applications in smart cities, traffic control, etc. In this work, we propose TIED, a text-to-image encoder-decoder model for the simultaneous extraction of visual and textual information for vehicle track retrieval. The model consists of an encoder network that enforces the two modalities into a common latent space and a decoder network that performs an inverse mapping to the text descriptions. The method exploits visual semantic attributes of a target vehicle along with a cycle-consistency loss. The proposed method employs both intra-modal and inter-modal relationships to improve retrieval performance.Our system yields competitive performance achieving the 7th position in the Natural Language-Based Vehicle Retrieval public track of the 2021 NVIDIA AI City Challenge. We demonstrate that the proposed TIED model obtains six times higher Mean Reciprocal Rank (MRR) than the baseline, achieving an MRR of 15.48. The code and models will be made publicly available.

show abstract

“…The organizers outlined the methods of leading teams in [19]. Zheng et al [29] trained real data with synthetic data by applying style transformation and content manipulation. Zhu et al [34] proposed an approach named VOC-ReID, taking the triplet vehicle-orientationcamera as a whole and reforming background/shape similarity as camera/orientation re-identification.…”

Section: Aicity20mentioning

confidence: 99%

An Empirical Study of Vehicle Re-Identification on the AI City Challenge

Luo¹,

Xu²,

Gu³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper introduces our solution for the Track2 in AI City Challenge 2021 (AICITY21). The Track2 is a vehicle re-identification (ReID) task with both the real-world data and synthetic data. We mainly focus on four points, i.e. training data, unsupervised domain-adaptive (UDA) training, post-processing, model ensembling in this challenge. (1) Both cropping training data and using synthetic data can help the model learn more discriminative features. (2) Since there is a new scenario in the test set that dose not appear in the training set, UDA methods perform well in the challenge. (3) Post-processing techniques including re-ranking, image-to-track retrieval, inter-camera fusion, etc, significantly improve final performance. (4) We ensemble CNN-based models and transformer-based models which provide different representation diversity. With aforementioned techniques, our method finally achieves 0.7445 mAP score, yielding the first place in the competition. Codes are available at https://github.com/ michuanhaohao/AICITY2021_Track2_DMT.

show abstract

Going Beyond Real Data: A Robust Visual Representation for Vehicle Re-identification

Cited by 43 publications

References 18 publications

Efficient virtual data search for annotation‐free vehicle reidentification

Efficient virtual data search for annotation‐free vehicle reidentification

TIED: A Cycle Consistent Encoder-Decoder Model for Text-to-Image Retrieval

An Empirical Study of Vehicle Re-Identification on the AI City Challenge

Contact Info

Product

Resources

About