LABNet: Local graph aggregation network with class balanced loss for vehicle re-identification

Taufique, Abu Md Niamul; Savakis, Andreas

doi:10.1016/j.neucom.2021.07.082

Cited by 14 publications

(8 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By employing specialized loss functions in a range of methods, the discriminative power of the features learned is enhanced, addressing specific challenges in the process [17]. Taufique and Savakis introduced Class Balanced Loss in the Local Graph Aggregation Network with Class Balanced Loss (LABNet) to compensate for sample distribution imbalances [17]. Wang et al used Triplet Center Loss in the Triplet Center Loss based Part-aware Model (TCPM) to emphasize part details and learn discriminating features [18].…”

Section: Loss Functionmentioning

confidence: 99%

See 1 more Smart Citation

Comparison and analysis of deep learning models for vehicle re-identification

Tang

2023

ACE

View full text Add to dashboard Cite

The rapid urbanization and increasing number of vehicles on the roads demand efficient and accurate vehicle re-identification (Re-ID) techniques for intelligent transportation systems, traffic monitoring, and surveillance applications. This paper offers a detailed analysis of deep learning approaches to vehicle Re-ID, covering feature learning, attention mechanism, unsupervised learning, self-supervised learning, and specialized loss function. The efficiency of these methods is assessed using VeRi-776 and VehicleID datasets. Key metrics, such as mean Average Precision (mAP) and Rank-n accuracy, are employed to gauge their success. Results show that feature learning, attention mechanism, and specialized loss function play pivotal roles in achieving high performance in vehicle Re-ID tasks, with unsupervised and self-supervised learning methods displaying potential for practical applications due to their scalability. The paper also highlights several challenges, including enhancing the interpretability of attention mechanisms, exploring the relationship between popular loss functions, and addressing the infeasibility of existing methods for real-time applications. The paper concludes with several recommendations for the prospects of vehicle Re-ID, including developing advanced real-time algorithms, enhancing deep learning techniques, investigating innovative approaches, and addressing existing challenges. These proposed advances could significantly improve the efficacy of feature learning and spark fresh innovations in this field.

show abstract

Section: Loss Functionmentioning

confidence: 99%

“…VeRi-776, extensively employed for vehicle Re-ID, comprises 49,325 samples depicting 776 distinct vehicles. They are recorded by 20 cameras in uncontrolled traffic situations [2,17]. The dataset, a comprehensive resource, includes a training (37,746 images) and a testing set (11,579 images) [2].…”

Section: Datasetmentioning

confidence: 99%

Comparison and analysis of deep learning models for vehicle re-identification

Tang

2023

ACE

View full text Add to dashboard Cite

show abstract

“…Because the features of night pattern images contain less information, and the network will have less ability to learn the similarity metric. We compare our method on VehicleID and VERI-Wild datasets with several state-of-the-art methods, including LABNet [17], LABNet-50 [17], PVEN [18] and DMML [19]. As shown in Tabs.…”

Section: Performance Evaluation and Comparisonmentioning

confidence: 99%

“…There are lots of night pattern images in these datasets, while other methods have not taken consideration into the cross domain problem. LABNet [17] 82.61 LABNet-50 [17] 81.05 PVEN [18] 82.53 Ours 92.55 LABNet [17] 89.63 LABNet-50 [17] 87.54 DMML [19] 87.37 Ours 95.72…”

Section: Performance Evaluation and Comparisonmentioning

confidence: 99%

Vehicle Matching Based on Similarity Metric Learning

Li¹,

Deng²,

Zhou³

2022

Journal of New Media

View full text Add to dashboard Cite

With the development of new media technology, vehicle matching plays a further significant role in video surveillance systems. Recent methods explored the vehicle matching based on the feature extraction. Meanwhile, similarity metric learning also has achieved enormous progress in vehicle matching. But most of these methods are less effective in some realistic scenarios where vehicles usually be captured in different times. To address this cross-domain problem, we propose a cross-domain similarity metric learning method that utilizes the GAN to generate vehicle images with another domain and propose the two-channel Siamese network to learn a similarity metric from both domains (i.e., Day pattern or Night pattern) for vehicle matching. To exploit properties and relationships among vehicle datasets, we first apply the domain transformer to translate the domain of vehicle images, and then utilize the two-channel Siamese network to extract features from both domains for better feature similarity learning. Experimental results illustrate that our models achieve improvements over state-of-the-arts.

show abstract

“…They play a central role in many downstream tasks about instance-level understanding, e.g. person search [1][2][3], visual reasoning [4,5], and human pose estimation [6][7][8]. Over the past few years, researches on object detection and instance segmentation have witnessed remarkable progresses, yielding good returns in flexible frameworks such as Faster region based convolutional neural networks (R-CNN) [9] and Mask R-CNN [10], and excellent performance on public benchmarks such as PASCAL-VOC [11] and MS-COCO [12].…”

Section: Introductionmentioning

confidence: 99%

DIM: long-tailed object detection and instance segmentation via dynamic instance memory

Chen,

Jin,

Zhang

et al. 2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Object detection and instance segmentation have been successful on benchmarks with relatively balanced category distribution (e.g., MSCOCO). However, state-of-the-art object detection and segmentation methods still struggle to generalize on long-tailed datasets (e.g., LVIS), where a few classes (head classes) dominate the instance samples, while most classes (tailed classes) have only a few samples. To address this challenge, we propose a plug-and-play module within the Mask R-CNN framework called Dynamic Instance Memory (DIM). Specifically, we augment Mask R-CNN with an auxiliary branch for training. It maintains a dynamic memory bank storing an instance-level prototype representation for each category, and shares the classifier with the existing instance branch. With a simple metric loss, the representations in DIM can be dynamically updated by the instance proposals in the mini-batch during training. Our DIM introduces a bias toward tailed classes to the classifier learning along with a class frequency reversed sampler, which learns generalizable representations from the original data distribution, complementing the existing instance branch. Comprehensive experiments on LVIS demonstrate the effectiveness of DIM, as well as the significant advantages of DIM over the baseline Mask R-CNN.

show abstract

LABNet: Local graph aggregation network with class balanced loss for vehicle re-identification

Cited by 14 publications

References 43 publications

Comparison and analysis of deep learning models for vehicle re-identification

Comparison and analysis of deep learning models for vehicle re-identification

Vehicle Matching Based on Similarity Metric Learning

DIM: long-tailed object detection and instance segmentation via dynamic instance memory

Contact Info

Product

Resources

About