Efficient Online Local Metric Adaptation via Negative Samples for Person Re-identification

Zhou, Jiahuan; Yu, Pei Lin; Tang, Wei; Wu, Ying

doi:10.1109/iccv.2017.265

Cited by 76 publications

(39 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They take advantage of deep neural networks [17,27,31,11] to construct a mapping from the data space to the embedding space so that the Euclidean distance in the embedding space can reflect the actual semantic distance between data points, i.e., a relatively large distance between inter-class samples and a relatively small distance between intra-class samples. Recently a variety of deep metric learning methods have been proposed and have demonstrated strong effectiveness in various tasks, such as image retrieval [30,23,19,5], person re-identification [26,37,48,2], and geo-localization [35,14,34]. Figure 1.…”

Section: Introductionmentioning

confidence: 99%

Hardness-Aware Deep Metric Learning

Zheng

Chen

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

141

109

View full text Add to dashboard Cite

This paper presents a hardness-aware deep metric learning (HDML) framework. Most previous deep metric learning methods employ the hard negative mining strategy to alleviate the lack of informative samples for training. However, this mining strategy only utilizes a subset of training data, which may not be enough to characterize the global geometry of the embedding space comprehensively. To address this problem, we perform linear interpolation on embeddings to adaptively manipulate their hard levels and generate corresponding label-preserving synthetics for recycled training, so that information buried in all samples can be fully exploited and the metric is always challenged with proper difficulty. Our method achieves very competitive performance on the widely used CUB-200-2011, Cars196, and Stanford Online Products datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

Hardness-Aware Deep Metric Learning

Zheng

Chen

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

141

109

View full text Add to dashboard Cite

show abstract

“…However, no such dataset exists at the moment and Geng et al [11] argue that creating such a dataset would be too costly. Accordingly, there is a focus on domain adaptation techniques using unlabeled data [12], [13], [14] from a deployment environment. Unsupervised domain adaptation is an important area of research that promises improved accuracy, but comes at the expense of a much more complex deployment model.…”

Section: Introductionmentioning

confidence: 99%

An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-identification

Marchwica

Jamieson

Siva

2018

2018 15th Conference on Computer and Robot Vision (CRV)

View full text Add to dashboard Cite

In recent years, a variety of proposed methods based on deep convolutional neural networks (CNNs) have improved the state of the art for large-scale person re-identification (ReID). While a large number of optimizations and network improvements have been proposed, there has been relatively little evaluation of the influence of training data and baseline network architecture. In particular, it is usually assumed either that networks are trained on labeled data from the deployment location (scene-dependent), or else adapted with unlabeled data, both of which complicate system deployment. In this paper, we investigate the feasibility of achieving scene-independent person ReID by forming a large composite dataset for training. We present an indepth comparison of several CNN baseline architectures for both scene-dependent and scene-independent ReID, across a range of training dataset sizes. We show that scene-independent ReID can produce leading-edge results, competitive with unsupervised domain adaption techniques. Finally, we introduce a new dataset for comparing within-camera and across-camera person ReID.

show abstract

“…On the VIPeR dataset, Table II shows that our method outperforms other models in the case when there is only one example for each person in each view. For example, our method achieves rank-1=51.3, which is noticeably improved performance compared to OL-MANS [16] with rank-1=44.9. The main reason is that the assumptions without supervision cannot provide the view-specific inference, and thus impedes these unsupervised methods from achieving higher accuracies.…”

Section: Resultsmentioning

confidence: 87%

“…a) Comparison to Un/semi-supervised Methods: We compared our method with several unsupervised re-ID models, including local salience learning based models (GST [11] and eSDC [12]), transfer-learning based models (t-LRDC [13], PUL [31], and UMDL [30]), metric learning methods (OSML [10], CAMEL [15], OL-MANS [16]), and a semi-supervised method of LSRO [14].…”

Section: Resultsmentioning

confidence: 99%

Cross-Entropy Adversarial View Adaptation for Person Re-identification

Hong

Wang

et al. 2019

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Person re-identification (re-ID) is a task of matching pedestrians under disjoint camera views. To recognise paired snapshots, it has to cope with large cross-view variations caused by the camera view shift. Supervised deep neural networks are effective in producing a set of non-linear projections that can transform cross-view images into a common feature space. However, they typically impose a symmetric architecture, yielding the network ill-conditioned on its optimisation. In this paper, we learn view-invariant subspace for person re-ID, and its corresponding similarity metric using an adversarial view adaptation approach. The main contribution is to learn coupled asymmetric mappings regarding view characteristics which are adversarially trained to address the view discrepancy by optimising the cross-entropy view confusion objective. To determine the similarity value, the network is empowered with a similarity discriminator to promote features that are highly discriminant in distinguishing positive and negative pairs. The other contribution includes an adaptive weighing on the most difficult samples to address the imbalance of within/between-identity pairs. Our approach achieves notable improved performance in comparison to state-of-the-arts on benchmark datasets.

show abstract

Efficient Online Local Metric Adaptation via Negative Samples for Person Re-identification

Cited by 76 publications

References 23 publications

Hardness-Aware Deep Metric Learning

Hardness-Aware Deep Metric Learning

An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-identification

Cross-Entropy Adversarial View Adaptation for Person Re-identification

Contact Info

Product

Resources

About