Cross Domain Knowledge Learning with Dual-branch Adversarial Network for Vehicle Re-identification

  title={Cross Domain Knowledge Learning with Dual-branch Adversarial Network for Vehicle Re-identification},
  author={Jinjia Peng and Huibing Wang and Xianping Fu},
The widespread popularization of vehicles has facilitated all people's life during the last decades. However, the emergence of a large number of vehicles poses the critical but challenging problem of vehicle re-identification (reID). Till now, for most vehicle reID algorithms, both the training and testing processes are conducted on the same annotated datasets under supervision. However, even a well-trained model will still cause fateful performance drop due to the severe domain bias between… 
Calibrated Domain-Invariant Learning for Highly Generalizable Large Scale Re-Identification
  • Ye Yuan, Wuyang Chen, +4 authors G. Hua
  • Computer Science
    2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2020
This work presents an adversarial domain-invariant feature learning framework (ADIN) that explicitly learns to separate identity-related features from challenging variations, where for the first time "free" annotations in ReID data such as video timestamp and camera index are utilized.
Multiview image generation for vehicle reidentification
A multi-view generative adversarial network that can synthesize real vehicle images conditioned on arbitrary skeleton views designed specifically for viewpoint normalization in vehicle ReID is proposed and shown that the features of the generated images and the original images are complementary.
Looking GLAMORous: Vehicle Re-Id in Heterogeneous Cameras Networks with Global and Local Attention
GLAMOR introduces several contributions: a better backbone construction method that outperforms recent approaches, group and layer normalization to address conflicting loss targets for re-id, a novel global attention module for global feature extraction, and a novel local Attention module for self-guided part-based local feature extraction that does not require supervision.
Robust, Extensible, and Fast: Teamed Classifiers for Vehicle Tracking and Vehicle Re-ID in Multi-Camera Networks.
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
Robust, Extensible, and Fast: Teamed Classifiers for Vehicle Tracking in Multi-Camera Networks
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 and describes an implementation for vehicle tracking and surveillance.
Vehicle Re-identification Based on Dual Distance Center Loss
This paper solves the shortcoming that center loss must combine with the softmax loss to supervise training the model, and proposes a dual distance center loss (DDCL) which strengthens the intra-class compactness of the center loss and enhances the generalization ability of center loss.
GiT: Graph Interactive Transformer for Vehicle Re-identification
This is the first work to combine graphs and transformers for vehicle re-identification to the best of the knowledge, and demonstrates that the method is superior to state-of-the-art approaches.
Cascade regression based on extreme learning machine for face alignment
This work proposes a fast and accurate online learning algorithm for face alignment that has a stronger prediction capability than conventional CR methods and is more accurate and efficient on still images or videos compared with the recent state-of-the-art approaches.
Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification
Extensive experiments on three large scale vehicle databases demonstrate that the proposed SGN is superior to state-of-the-art vehicle re-identification approaches and a novel pyramidal graph network is designed to comprehensively explore the spatial significance of feature maps at multiple scales.


Group-Sensitive Triplet Embedding for Vehicle Reidentification
A deep metric learning method, group-sensitive-triplet embedding (GS-TRE), to recognize and retrieve vehicles, in which intraclass variance is elegantly modeled by incorporating an intermediate representation “group” between samples and each individual vehicle in the triplet network learning.
Vehicle Re-Identification by Deep Hidden Multi-View Inference
This paper proposes two end-to-end deep architectures: the Spatially Concatenated ConvNet and convolutional neural network (CNN)-LSTM bi-directional loop and exploits the great advantages of the CNN and long short-term memory (L STM) to learn transformations across different viewpoints of vehicles.
Person Transfer GAN to Bridge Domain Gap for Person Re-identification
A Person Transfer Generative Adversarial Network (PTGAN) is proposed to relieve the expensive costs of annotating new training samples and comprehensive experiments show that the domain gap could be substantially narrowed-down by the PTGAN.
PROVID: Progressive and Multimodal Vehicle Reidentification for Large-Scale Urban Surveillance
This paper proposes PROVID, a PROgressive Vehicle re-IDentification framework based on deep neural networks, which not only utilizes the multimodality data in large-scale video surveillance, such as visual features, license plates, camera locations, and contextual information, but also considers vehicle reidentification in two progressive procedures: coarse- to-fine search in the feature domain, and near-to-distantsearch in the physical space.
Cross-Domain Person Reidentification Using Domain Adaptation Ranking SVMs
Experimental results show that the proposed AdaRSVM outperforms existing supervised or unsupervised, learning or non-learning reidentification methods without using label information in target cameras and achieves better reIdentification performance than existing domain adaptation methods derived under equal conditional probability assumption.
Cross-Entropy Adversarial View Adaptation for Person Re-Identification
This work learns view-invariant subspace for person re-ID, and its corresponding similarity metric using an adversarial view adaptation approach, and achieves notably improved performance in comparison with the state-of-the-arts on benchmark datasets.
EANet: Enhancing Alignment for Cross-Domain Person Re-identification
This paper proposes Part Aligned Pooling (PAP) that brings significant improvement for cross-domain testing and designs a Part Segmentation (PS) constraint over ReID feature to enhance alignment and improve model generalization and shows that applying the PS constraint to unlabeled target domain images serves as effective domain adaptation.
Deep Relative Distance Learning: Tell the Difference between Similar Vehicles
A Deep Relative Distance Learning (DRDL) method is proposed which exploits a two-branch deep convolutional network to project raw vehicle images into an Euclidean space where distance can be directly used to measure the similarity of arbitrary two vehicles.
Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification
This work introduces an Transferable Joint Attribute-Identity Deep Learning (TJ-AIDL) for simultaneously learning an attribute-semantic and identity-discriminative feature representation space transferrable to any new (unseen) target domain for re-id tasks without the need for collecting new labelled training data from the target domain.