Hard sample mining makes person re-identification more efficient and accurate

Chen, Kezhou; Chen, Yang; Han, Chuchu; Sang, Nong; Gao, Changxin

doi:10.1016/j.neucom.2019.11.094

Cited by 26 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, according to Table 1, it can be seen that the algorithm proposed in this paper has better recognition performance than the traditional machine learning pedestrian recognition algorithm proposed in [36] and the deep learning pedestrian recognition algorithm proposed in [37,38]. It proves the advantages of the proposed algorithm.…”

Section: Analysis Of Experimentalmentioning

confidence: 55%

“…It shows that traditional machine learning pedestrian recognition methods are the worst of the categories listed above. The mAP indicators obtained by the deep learning pedestrian recognition methods proposed in [37,38] are higher than 60%, and the rank-1 indicators are higher than 80%. They are each more than 7% higher than traditional machine learning methods.…”

Section: Analysis Of Experimentalmentioning

confidence: 84%

“…Ali and Chaudhuri [36] pointed out that they demonstrate the robustness of the training procedure with respect to the random initialization, the positive effect of pretraining in terms of optimization, and its role as a regularizer. Chen et al [37] also proposed a fast greedy algorithm to train deep learning models and achieved good results. Han et al [38] proposed a Spiking Neural Networks.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Pedestrian Reidentification Algorithm Based on Deconvolution Network Feature Extraction‐Multilayer Attention Mechanism Convolutional Neural Network

Liu

Lei

2021

Journal of Sensors

View full text Add to dashboard Cite

Pedestrian reidentification is a key technology in large-scale distributed camera systems. It can quickly and efficiently detect and track target people in large-scale distributed surveillance networks. The existing traditional pedestrian reidentification methods have problems such as low recognition accuracy, low calculation efficiency, and weak adaptive ability. Pedestrian reidentification algorithms based on deep learning have been widely used in the field of pedestrian reidentification due to their strong adaptive ability and high recognition accuracy. However, the pedestrian recognition method based on deep learning has the following problems: first, during the learning process of the deep learning model, the initial value of the convolution kernel is usually randomly assigned, which makes the model learning process easily fall into a local optimum. The second is that the model parameter learning method based on the gradient descent method exhibits gradient dispersion. The third is that the information transfer of pedestrian reidentification sequence images is not considered. In view of these issues, this paper first examines the feature map matrix from the original image through a deconvolution neural network, uses it as a convolution kernel, and then performs layer-by-layer convolution and pooling operations. Then, the second derivative information of the error function is directly obtained without calculating the Hessian matrix, and the momentum coefficient is used to improve the convergence of the backpropagation, thereby suppressing the gradient dispersion phenomenon. At the same time, to solve the problem of information transfer of pedestrian reidentification sequence images, this paper proposes a memory network model based on a multilayer attention mechanism, which uses the network to effectively store image visual information and pedestrian behavior information, respectively. It can solve the problem of information transmission. Based on the above ideas, this paper proposes a pedestrian reidentification algorithm based on deconvolution network feature extraction-multilayer attention mechanism convolutional neural network. Experiments are performed on the related data sets using this algorithm and other major popular human reidentification algorithms. The results show that the pedestrian reidentification method proposed in this paper not only has strong adaptive ability but also has significantly improved average recognition accuracy and rank-1 matching rate compared with other mainstream methods.

show abstract

Section: Analysis Of Experimentalmentioning

confidence: 55%

Section: Analysis Of Experimentalmentioning

confidence: 84%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Pedestrian Reidentification Algorithm Based on Deconvolution Network Feature Extraction‐Multilayer Attention Mechanism Convolutional Neural Network

Liu

Lei

2021

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…It has great randomness, which is not conducive to the specific optimization of the model. In [8], the authors propose a new adaptive hard sample mining algorithm for person re-identification task. Through comprehensive comparison of the hard level differences between training batches and the differences in demand for hard sample numbers, the model is optimized and the accuracy is improved.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Bird’s Nest Detection on Transmission Lines Using UAV Imagery

Yan

Luan

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

In order to ensure the safety of transmission lines, the use of unmanned aerial vehicle (UAV) images for automatic object detection has important application prospects, such as the detection of birds’ nests. The traditional bird’s nest detection methods mainly include the study of morphological characteristics of the bird’s nest. These methods have poor applicability and low accuracy. In this work, we propose a deep learning-based birds’ nests automatic detection framework—region of interest (ROI) mining faster region-based convolutional neural networks (RCNN). First, the prior dimensions of anchors are obtained by using k-means clustering to improve the accuracy of coordinate boxes generation. Second, in order to balance the number of foreground and background samples in the training process, the focal loss function is introduced in the region proposal network (RPN) classification stage. Finally, the ROI mining module is added to solve the class imbalance problem in the classification stage, combined with the characteristics of difficult-to-classify bird’s nest samples in the UAV images. After parameter optimization and experimental verification, the deep learning-based bird’s nest automatic detection framework proposed in this work achieves high detection accuracy. In addition, the mean average precision (mAP) and formula 1 (F1) score of the proposed method are higher than the original faster RCNN and cascade RCNN. Our comparative analysis verifies the effectiveness of the proposed method.

show abstract

“…Though they achieved considerable progress in the development of person re-id, it still meets unresolved challenging situations due to the large variations in pose state, illumination intensity, random occlusion, even real-time switching background and camera views. With the development of deep learning technology, plenty of person re-id models paid attention to supervised learning [2], [28], [32], which has proved to be effective. Though they achieved several successful applications in The associate editor coordinating the review of this manuscript and approving it for publication was Lefei Zhang .…”

Section: Introductionmentioning

confidence: 99%

Multi-Source Transfer Network for Cross Domain Person Re-Identification

Wang

Zhang

2020

IEEE Access

View full text Add to dashboard Cite

Unsupervised person re-identification has been improved significantly by the development of cross domain person re-identification models, which apply useful knowledge in source data to completely unlabeled target data. However, existing cross domain re-identification models still remain a major limitation that they are all based on single-source and single-target setting. The only one source domain may remain a tremendous gap between target, generating negative effect for the model training in target domain. To overcome this drawback, this paper proposes a Multi-Source Transfer Network to learn a shared target-biased feature space between multi-source and target domains, which achieves transfer learning in feature-level, pixel-level, and task-level by the proposed target-biased multi-source transfer learning module, relativistic adversarial learning module, and task-gap bridging module, respectively. Through leveraging the domain gaps in feature-level, pixel-level, and task-level, this network can synthetically learn a discriminative model from multiple source domains to effectively conduct re-identification in target domain. Furthermore, this paper conducts extensive experiments on three widely-recognized person re-identification datasets, and the proposed network achieves rank-1 accuracies of 80.9% and 74.6% on DukeMTMC-reID and Market-1501 datasets, respectively. The results demonstrate the contribution of the proposed method, compared with state-of-the-art methods, including hand-crated feature, clustering and transfer learning based methods. INDEX TERMS Multi-source transfer, relativistic discriminator, cross domain, person re-identification.

show abstract

Hard sample mining makes person re-identification more efficient and accurate

Cited by 26 publications

References 8 publications

Pedestrian Reidentification Algorithm Based on Deconvolution Network Feature Extraction‐Multilayer Attention Mechanism Convolutional Neural Network

Pedestrian Reidentification Algorithm Based on Deconvolution Network Feature Extraction‐Multilayer Attention Mechanism Convolutional Neural Network

Deep Learning-Based Bird’s Nest Detection on Transmission Lines Using UAV Imagery

Multi-Source Transfer Network for Cross Domain Person Re-Identification

Contact Info

Product

Resources

About