Relative Distance Metric Leaning Based on Clustering Centralization and Projection Vectors Learning for Person Re-Identification

Ni, Tongguang; Ding, Zongyuan; Chen, Fuhua; Wang, Hongyuan

doi:10.1109/access.2018.2795020

Cited by 17 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We design 10 classification tasks, and the basic information of tasks is as shown in Table 2 . In order to show the performance of our method, we compare AMDML with four single-view classification methods [including DMSI (Xing et al, 2003 ), large margin nearest neighbor (LMNN) (Weinberger and Saul, 2009 ), neighborhood preserving embedding (NPE) (Wen et al, 2010 ), and RDML-CCPVL (Ni et al, 2018 )] and three multi-view methods [including MvCVM (Huang et al, 2015 ), VMRML-LS (Quang et al, 2013 ), and DMML (Zhang et al, 2019 )]. In the LMNN method, the number of target neighbors k was set to k = 3, and the weighting parameter μ is selected within the grid {0, 0.2,., 1}.…”

Section: Methodsmentioning

confidence: 99%

Auto-Weighted Multi-View Discriminative Metric Learning Method With Fisher Discriminative and Global Structure Constraints for Epilepsy EEG Signal Classification

Xue

2020

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

Metric learning is a class of efficient algorithms for EEG signal classification problem. Usually, metric learning method deals with EEG signals in the single view space. To exploit the diversity and complementariness of different feature representations, a new a uto-weighted m ulti-view d iscriminative m etric l earning method with Fisher discriminative and global structure constraints for epilepsy EEG signal classification called AMDML is proposed to promote the performance of EEG signal classification. On the one hand, AMDML exploits the multiple features of different views in the scheme of the multi-view feature representation. On the other hand, considering both the Fisher discriminative constraint and global structure constraint, AMDML learns the discriminative metric space, in which the intraclass EEG signals are compact and the interclass EEG signals are separable as much as possible. For better adjusting the weights of constraints and views, instead of manually adjusting, a closed form solution is proposed, which obtain the best values when achieving the optimal model. Experimental results on Bonn EEG dataset show AMDML achieves the satisfactory results.

show abstract

Section: Methodsmentioning

confidence: 99%

Auto-Weighted Multi-View Discriminative Metric Learning Method With Fisher Discriminative and Global Structure Constraints for Epilepsy EEG Signal Classification

Xue

2020

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…This kind of clustering and training process usually alternates until the model is stable. For example, Ni et al [39] proposed a relative metric learning method based on clustering and projection vector learning; Wu et al [40] proposed a hierarchical clustering algorithm for inter-camera and cross-camera shooting, and Fan et al [29] added a selection operation between clustering and fine-tuning to improve the optimization effect of the model. However, these models are usually interfered by noise pseudo-label.…”

Section: Cross-domain Problemmentioning

confidence: 99%

Person Re-Identification by Effective Features and Self-Optimized Pseudo-Label

Gao

Guan

et al. 2021

IEEE Access

View full text Add to dashboard Cite

With the development of deep learning, person re-identification (ReID) has been widely concerned and studied. At present, in practical application, there are three main problems in person ReID: first, it is difficult to locate the target person because the person is frequently partially occluded in crowed scenes; second, it is difficult to match the target person due to the similarity of the target person and other pedestrian features; third, the problem of model performance degradation caused by the large style discrepancies across domain/datasets. These three problems greatly limit the application of person ReID in real scenes. To solve these problems, we proposed a person ReID method based on effective features and self-optimized pseudo-label. Firstly, we designed a feature aggregation module which combines mask channel and pose channel to accurately extract the global saliency features, so as to solve the occlusion problem; secondly, we designed a head-shoulder feature auxiliary module to enhance the feature representation of the head-shoulder, so as to solve the problem of similarity between the target person and other pedestrian features; finally, we designed a self-optimized pseudo-label training module to improves the generalization ability of the model, so as to solve the problem of different styles in the cross-domain environment. Extensive contrast experiments with the state-of-the-art methods on multiple person re-ID datasets show that our method leads to significant improvement, which prove the effectiveness of our method.

show abstract

“…Existing approaches for the person Re-ID can be divided into two aspects: feature extraction [15]- [19] or distance learning [8], [9], [20]- [22] to directly learn the projections of data items from different camera views into a common feature representation subspace, in which the similarity between them can be assessed directly [5]- [7], [23]. The diagram of our proposed JAFN model.…”

Section: Related Workmentioning

confidence: 99%

Joint Attentive Spatial-Temporal Feature Aggregation for Video-Based Person Re-Identification

2019

View full text Add to dashboard Cite

Video-based person re-identification (Re-ID) remains to be a promising but challenging computer vision task, suffering from a lack of discriminative features that better aggregate both the spatial and temporal information. In this paper, we propose a joint attentive spatial-temporal feature aggregation network (JAFN) for the video-based person Re-ID, simultaneously learning the quality-and frame-aware model to obtain attention-based spatial-temporal feature aggregation. Specifically, we utilize CNN to learn the spatial features, while introducing the LSTM to separately learn the temporal features. For the feature aggregation, we introduce two attention mechanisms respectively for generating the quality and frame significance score, where the quality score measures the quality of the images for attentive spatial feature aggregation, and the frame score measures the significance of the image frames contributing to the temporal feature. Then, we utilize the set-pooling for both the quality-aware spatial feature and the frame-aware temporal feature aggregation based on the attentive scores. The residual learning is also introduced to play between the LSTM and the CNN for adaptive spatial-temporal feature fusion. Furthermore, we adopt the data balance to alleviate the data disproportions existing in datasets of the video-based Re-ID. The extensive experimental results conducted on the PRID2011, i-LIDS-VID, and MARS datasets demonstrate the effectiveness of the proposed JAFN. Furthermore, comparison results conducted on different modules and features in the JAFN show that our approach is of favorable generalization ability on attentively aggregating both the spatial and temporal features.

show abstract

Relative Distance Metric Leaning Based on Clustering Centralization and Projection Vectors Learning for Person Re-Identification

Cited by 17 publications

References 22 publications

Auto-Weighted Multi-View Discriminative Metric Learning Method With Fisher Discriminative and Global Structure Constraints for Epilepsy EEG Signal Classification

Auto-Weighted Multi-View Discriminative Metric Learning Method With Fisher Discriminative and Global Structure Constraints for Epilepsy EEG Signal Classification

Person Re-Identification by Effective Features and Self-Optimized Pseudo-Label

Joint Attentive Spatial-Temporal Feature Aggregation for Video-Based Person Re-Identification

Contact Info

Product

Resources

About