Diversity-Achieving Slow-DropBlock Network for Person Re-Identification

Wu, Xiaofu; Xie, Ben; Zhao, Shiliang; Zhang, Suofei; Xiao, Yong; Li, Ming

doi:10.48550/arxiv.2002.04414

Cited by 2 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Batch DropBlock Network (BDB) [5] uses a global branch and a feature dropping branch to keep the global salient representations and reinforce the attentive feature learning of local regions. Wu [34] uses multiple dropping branches on the basis of BDB to further boost the performance.…”

Section: Dropblockmentioning

confidence: 99%

Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond

Wang¹,

Zhao²,

Liao³

et al. 2020

Preprint

View full text Add to dashboard Cite

Unsupervised domain adaptation (UDA) for person re-identification is challenging because of the huge gap between the source and target domain. A typical selftraining method is to use pseudo-labels generated by clustering algorithms to iteratively optimize the model on the target domain. However, a drawback to this is that noisy pseudo-labels generally cause troubles in learning. To address this problem, a mutual learning method by dual networks has been developed to produce reliable soft labels. However, as the two neural networks gradually converge, their complementarity is weakened and they likely become biased towards the same kind of noise. In this paper, we propose a novel light-weight module, the Attentive WaveBlock (AWB), which can be integrated into the dual networks of mutual learning to enhance the complementarity and further depress noise in the pseudo-labels. Specifically, we first introduce a parameter-free module, the WaveBlock, which creates a difference between two networks by waving blocks of feature maps differently. Then, an attention mechanism is leveraged to enlarge the difference created and discover more complementary features. Furthermore, two kinds of combination strategies, i.e. pre-attention and post-attention, are explored. Experiments demonstrate that the proposed method achieves state-of-theart performance with significant improvements of 9.4%, 5.9%, 7.4%, and 7.7% in mAP on Duke-to-Market, Market-to-Duke, Duke-to-MSMT, and Market-to-MSMT UDA tasks, respectively.

show abstract

Section: Dropblockmentioning

confidence: 99%

Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond

Wang¹,

Zhao²,

Liao³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Person Re-ID has made remarkable achievements in the training and testing of single-domain data sets [8,9]. However, in the cross-domain case (training on a source domain, testing on a target domain) but the performance of the model will be greatly compromised if a new data set is re-identified by using the pre-trained model directly.…”

Section: Introductionmentioning

confidence: 99%

Part‐level attention networks for cross‐domain person re‐identification

Qun

Du²,

Ouyang³

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

Person re-identification (Re-ID) is in significant demand for intelligent security and single or multiple-target tracking. However, there are issues in the person Re-ID tasks, such as sharp decline in cross-data sets detection accuracy, poor generalization and cross-domain ability of the model. This work mainly studies the generalization and adaptation of crossdomain person Re-ID models. Different from most existing methods for cross-domain Re-ID tasks, the authors use diversified spatial semantic feature in pixel-level learning in the target domain to improve the generality and adaptability of the model. In the case that no information of the target domain is used during the model training, the trained model is directly tested on the data set of the target domain. It has proven effective to add the attention cascade module into the backbone network combining with the part-level branch. The authors conducted extensive experiments based on the three data sets of Market-1501, DukeMTMC-ReID and MSMT17, resulting in both single-domain and cross-domain tests with an average improvement of Rank1 and mAP values of about 10% compared with Baseline through the authors' proposed method named Part-Level Attention Network.

show abstract

Diversity-Achieving Slow-DropBlock Network for Person Re-Identification

Cited by 2 publications

References 48 publications

Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond

Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond

Part‐level attention networks for cross‐domain person re‐identification

Contact Info

Product

Resources

About