Cross domain knowledge learning with dual-branch adversarial network for vehicle re-identification

Peng, Jinjia; Wang, Huibing; Xu, Fengqiang; Fu, Xianping

doi:10.1016/j.neucom.2020.02.112

Cited by 31 publications

(14 citation statements)

References 37 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the difference in feature aggregation structure, we can subdivide it into global feature learning methods and local feature learning methods. The global feature learning methods [2,5,21,33,[35][36][37][38][39][40][41][42][43][44][45][46] usually have a spatial global pooling layer to compress the entire vehicle features. However, due to the characteristic of spatial global pooling layers, discriminative local features will inevitably be underestimated, which is detrimental to vehicle re-identification.…”

Section: A Vehicle Re-identificationmentioning

confidence: 99%

GiT: Graph Interactive Transformer for Vehicle Re-identification

Shen¹,

Xie²,

Zhu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Transformers are more and more popular in computer vision, which treat an image as a sequence of patches and learn robust global features from the sequence. However, a suitable vehicle re-identification method should consider both robust global features and discriminative local features. In this paper, we propose a graph interactive transformer (GiT) for vehicle re-identification. On the whole, we stack multiple GiT blocks to build a competitive vehicle re-identification model, in where each GiT block employs a novel local correlation graph (LCG) module to extract discriminative local features within patches and uses a transformer layer to extract robust global features among patches. In detail, in the current GiT block, the LCG module learns local features from local and global features resulting from the LCG module and transformer layer of the previous GiT block. Similarly, the transformer layer learns global features from the global features generated by the transformer layer of the previous GiT block and the new local features outputted via the LCG module of the current GiT block. Therefore, LCG modules and transformer layers are in a coupled status, bringing effective cooperation between local and global features. This is the first work to combine graphs and transformers for vehicle re-identification to the best of our knowledge. Extensive experiments on three large-scale vehicle reidentification datasets demonstrate that our method is superior to state-of-the-art approaches. The code will be available soon.

show abstract

Section: A Vehicle Re-identificationmentioning

confidence: 99%

GiT: Graph Interactive Transformer for Vehicle Re-identification

Shen¹,

Xie²,

Zhu³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Challenges lie in re-id under adversarial conditions where vehicles need to be tracked with multi-orientation, multi-scale, multi-resolution values alongside possible occlusion and blur. The vehicle reidentification problem has seen significant work in the past few years due to advances in the general one-shot learning problem [10], [15], [16], [17], [18], [19], [20]. • Event detection: Automated event detection remains a difficult challenge due to the lack of labeled real-world or synthetic data and absence of frameworks for video-based anomaly detection.…”

Section: A Classic Vehicle Tracking Approaches and Research Issuesmentioning

confidence: 99%

“…Conversely, existing vehicle re-id datasets such as VeRi-776 [35] and VeRi-Wild [36] primarily focus on intraclass variability. Current approaches in vehicle re-id attempt to address inter-class similarity and intra-class variability in the same end-to-end model [16], [17], [18], [20]. This creates models that sacrifice performance on solving edge cases in intra-class variability to increase discriminative ability for interclass similarity across the entire data space.…”

Section: B Research Issues In Teamed Classifiersmentioning

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

mentioning

confidence: 99%

“…), VAMI + STRZhou and Shao (2018a),MTCRO Xu et al (2018), QD-DLFZhu et al (2019),PAMAL Tumrani et al (2020) and DAN + ATTNet (DAVR)Peng et al (2020), and then, compare them with the proposed DDCL. The unsupervised DAN + ATTNet (DAVR)Peng et al (2020) and the FACT + STRLiu et al (2016d) which combined the traditional features and deep features performed relatively poorly. While OIFEWang et al (2017), S-CNN + P-LSTMShen et al (2017),RAM Liu et al (2018), VAMI + STRZhou and Shao (2018a),MTCRO Xu et al (2018), QD-DLFZhu et al (2019),PAMAL Tumrani et al (2020) and DAN + ATTNet(DAVR)Peng et al (2020) use softmax loss as a supervising tools to train their models, after removing softmax loss, the experimental results of DDCL are exceed that of these methods.…”

mentioning

confidence: 99%

Vehicle Re-identification Based on Dual Distance Center Loss

Hu,

Xu,

Wen

et al. 2020

Preprint

View full text Add to dashboard Cite

Recently, deep learning has been widely used in the field of vehicle re-identification.When training a deep model, softmax loss is usually used as a supervision tool. However, the softmax loss performs well for closed-set tasks, but not very well for open-set tasks. In this paper, we sum up five shortcomings of center loss and solved all of them by proposing a dual distance center loss (DDCL). Especially we solve the shortcoming that center loss must combine with the softmax loss to supervise training the model, which provides us with a new perspective to examine the center loss. In addition, we verify the inconsistency between the proposed DDCL and softmax loss in the feature space, which makes the center loss no longer be limited by the softmax loss in the feature space after removing the softmax loss. To be specifically, we add the Pearson distance on the basis of the Euclidean distance to the same center, which makes all features of the same class be confined to the intersection of a hypersphere and a hypercube in the feature space. The proposed Pearson distance strengthens the intra-class compactness of the center loss and enhances the generalization ability of center loss. Moreover, by designing a Euclidean distance threshold between all center pairs, which not only strengthens the inter-class separability of center loss, but also makes the center loss (or DDCL) works well without the combination of softmax loss. We apply DDCL in the field of vehicle re-identification named

show abstract

Cross domain knowledge learning with dual-branch adversarial network for vehicle re-identification

Cited by 31 publications

References 37 publications

GiT: Graph Interactive Transformer for Vehicle Re-identification

GiT: Graph Interactive Transformer for Vehicle Re-identification

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

Vehicle Re-identification Based on Dual Distance Center Loss

Contact Info

Product

Resources

About