Unsupervised person re-identification based on self-distilled vision Transformer

doi:10.11772/j.issn.1001-9081.2024040425

Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (9): 2893-2902.DOI: 10.11772/j.issn.1001-9081.2024040425

• Multimedia computing and computer simulation • Previous Articles Next Articles

Unsupervised person re-identification based on self-distilled vision Transformer

Jieru JIA¹^,²^,³(), Jianchao YANG¹^,²^,³, Shuorui ZHANG¹^,²^,³, Tao YAN¹^,²^,⁴^,⁵, Bin CHEN⁴^,⁵

^1.Institute of Big Data Science and Industry，Shanxi University，Taiyuan Shanxi 030006，China
^2.School of Computer and Information Technology，Shanxi University，Taiyuan Shanxi 030006，China
^3.Engineering Research Center for Machine Vision and Data Mining of Shanxi Province （Shanxi University），Taiyuan Shanxi 030006，China
^4.Chongqing Research Institute of Harbin Institute of Technology，Chongqing 401151，China
^5.International Research Institute of Artificial Intelligence，Harbin Institute of Technology，Shenzhen Guangdong 518055，China

Received:2024-04-09 Revised:2024-06-18 Accepted:2024-06-26 Online:2024-09-14 Published:2024-09-10
Contact: Jieru JIA
About author:YANG Jianchao， born in 2001， M. S. candidate. His research interests include vision Transformer.
ZHANG Shuorui， born in 1999， M. S. candidate. Her research interests include unsupervised learning.
YAN Tao， born in 1987， Ph. D.， associate professor. His research interests include 3D reconstruction.
CHEN Bin， born in 1970， Ph. D.， professor. His research interests include computer vision.
Supported by:
National Natural Science Foundation of China(62106133);Funds for Central-Government-Guided Local Science and Technology Development(YDZJSX20231C001)

基于自蒸馏视觉Transformer的无监督行人重识别

贾洁茹¹^,²^,³(), 杨建超¹^,²^,³, 张硕蕊¹^,²^,³, 闫涛¹^,²^,⁴^,⁵, 陈斌⁴^,⁵

^1.山西大学大数据科学与产业研究院, 太原 030006
^2.山西大学计算机与信息技术学院, 太原 030006
^3.山西省机器视觉与数据挖掘工程研究中心(山西大学), 太原 030006
^4.哈尔滨工业大学重庆研究院, 重庆 401151
^5.哈尔滨工业大学(深圳)国际人工智能研究院, 广东深圳 518055

通讯作者: 贾洁茹
作者简介:杨建超（2001—），男，山西运城人，硕士研究生，主要研究方向：视觉Transformer
张硕蕊（1999—），女，山西运城人，硕士研究生，主要研究方向：无监督学习
闫涛（1987—），男，山西定襄人，副教授，博士，主要研究方向：三维重建
陈斌（1970—），男，四川广汉人，教授，博士，主要研究方向：机器视觉。
基金资助:
国家自然科学基金资助项目(62106133);中央引导地方科技发展资金资助项目(YDZJSX20231C001)

Abstract

Abstract:

Since the lack of inductive bias in Vision Transformer （ViT） makes it hard to learn meaningful visual representations on relatively small-scale datasets， an unsupervised person re-identification method based on self-distilled vision Transformer was proposed. Firstly， because of the modular architecture of ViT， the feature generated by any intermediate block has the same dimension， so an intermediate Transformer block was selected randomly and was fed into the classifier to obtain prediction results. Secondly， by using the Kullback-Leibler divergence between the minimized randomly selected intermediate classifier output and the final classifier output distribution， the classification prediction results of the intermediate block were constrained to be consistent with the results of the final classifier， and a self-distillation loss function was constructed based on this. Finally， the model was optimized by jointly minimizing the cluster-level contrast loss， instance-level contrast loss， and self-distillation loss. Besides by providing soft supervision from the final classifier to the intermediate block， the inductive bias was introduced to ViT model effectively， so that the model was able to learn more robust and generalized visual representations. Compared to Transformer-based Object Re-IDentification Self-Supervised Learning （TransReID-SSL）， the proposed method improves the mean Average Precision （mAP） and Rank-1 by 1.2 and 0.8 percentage points respectively on Market-1501 dataset， and by 3.4 and 3.1 percentage points respectively on MSMT17 dataset. Experimental results demonstrate that the proposed method can increase the unsupervised person re-identification precision effectively.

Key words: person re-identification, unsupervised learning, Vision Transformer (ViT), knowledge distillation, feature representation

摘要：

针对视觉Transformer（ViT）缺乏归纳偏置，导致在相对小规模的行人重识别数据上难以学习有意义的视觉表征的问题，提出一种基于自蒸馏视觉Transformer的无监督行人重识别方法。首先，利用ViT的模块化架构，即每个中间块生成的特征维度相同的特性，随机选择一个中间Transformer块并将它送入分类器以得到预测结果；其次，通过最小化随机选择的中间分类器输出与最终分类器输出分布之间的Kullback-Leibler散度，约束中间块的分类预测结果与最终分类器的结果保持一致，据此构建自蒸馏损失函数；最后，通过对聚类级对比损失、实例级对比损失和自蒸馏损失进行联合最小化，对模型进行优化。此外，通过从最终分类器向中间块提供软监督，有效地给ViT模型引入归纳偏置，进而有助于模型学习更鲁棒和通用的视觉表征。与基于TransReID的自监督学习（TransReID-SSL）相比，在Market-1501数据集上，所提方法的平均精度均值（mAP）和Rank-1分别提升1.2和0.8个百分点；在MSMT17数据集上，所提方法的mAP和Rank-1分别提升3.4和3.1个百分点。实验结果表明，所提方法能够有效提高无监督行人重识别的精度。

关键词: 行人重识别, 无监督学习, 视觉Transformer, 知识蒸馏, 特征表示

CLC Number:

TP391.4

Jieru JIA, Jianchao YANG, Shuorui ZHANG, Tao YAN, Bin CHEN. Unsupervised person re-identification based on self-distilled vision Transformer[J]. Journal of Computer Applications, 2024, 44(9): 2893-2902.

贾洁茹, 杨建超, 张硕蕊, 闫涛, 陈斌. 基于自蒸馏视觉Transformer的无监督行人重识别[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2893-2902.

Figures/Tables 10

Fig. 1 Flow of proposed method

Tab. 1 Comparison results of different methods on Market-1501 dataset

类别	方法	Market-1501
类别	方法	backbone	源域	mAP	Rank-1	Rank-5	Rank-10
UDA	MMCL	ResNet	Duke	60.4	84.4	92.8	95.0
	UNRN	ResNet	MSMT17	75.6	89.3	95.8	97.5
	SPCL	ResNet	MSMT17	77.5	89.7	96.1	97.6
USL	BUC	ResNet	None	38.3	66.2	79.6	84.5
	SSL	ResNet	None	37.8	71.7	83.8	87.4
	MMCL	ResNet	None	45.5	80.3	89.4	92.3
	HCT	ResNet	None	56.4	80.0	91.6	95.2
	CycAs	ResNet	None	64.8	84.8	—	—
	UGA	ResNet	None	70.3	87.2	—	—
	SPCL	ResNet	None	73.1	88.1	95.1	97.0
	C-Contrast	ResNet	None	82.1	92.3	96.7	97.9
	HHCL	ResNet	None	83.0	92.7	97.3	98.1
	TransReID-SSL	ViT-S	None	88.2	94.2	—	—
	TransCL	ViT-S	None	76.6	89.6	95.3	—
	PSD	ViT-S	None	80.1	92.0	97.2	98.5
	本文方法	ViT-S	None	89.4	95.0	98.0	98.7

Tab. 2 Comparison results of different methods on MSMT17 dataset

方法		MSMT17
方法		backbone	源域	mAP	Rank-1	Rank-5	Rank-10
UDA	ECN	ResNet	Duke	10.2	30.2	41.5	46.8
	UNRN	ResNet	Market-1501	24.0	50.1	63.5	69.3
	SPCL	ResNet	Market-1501	26.8	53.7	65.0	69.8
USL	MMCL	ResNet	None	11.2	35.4	44.8	49.8
	TAUDL	ResNet	None	12.5	28.4	—	—
	CycAs	ResNet	None	26.7	50.1	—	—
	UGA	ResNet	None	21.7	49.5	—	—
	SPCL	ResNet	None	19.1	42.3	55.6	61.2
	C-Contrast	ResNet	None	27.6	56.0	66.8	71.5
	HHCL	ResNet	None	26.3	52.3	64.2	69.6
	TransReID-SSL	ViT-S	None	40.9	66.4	—	—
	TransCL	ViT-S	None	19.2	39.1	50.4	—
	PSD	ViT-S	None	38.4	61.7	70.2	73.4
	本文方法	ViT-S	None	44.3	69.5	74.1	78.2

Tab. 3 Comparison results of different block selection strategies

模型	Market-1501			MSMT17
模型	mAP	Rank-1	mAP	Rank-1
ViT-Baseline	88.2	94.2	40.9	66.4
ViT+SD［0，5］	88.4	94.5	41.7	66.9
ViT+SD［6，11］	88.9	94.9	42.4	67.6
ViT+SD［all blocks］	89.4	95.0	44.3	69.5

Tab. 4 Influence of temperature parameter on model precision

参数 $τ s d$	Market-1501		MSMT17
参数 $τ s d$	mAP/%	Rank-1/%	mAP/%	Rank-1/%
1.0	88.6	94.1	43.9	69.0
2.0	88.9	94.4	43.1	68.8
3.0	89.4	95.0	44.3	69.5
4.0	89.0	94.8	43.0	68.1

Tab. 4 Influence of temperature parameter on model precision

参数 $τ s d$	Market-1501		MSMT17
参数 $τ s d$	mAP/%	Rank-1/%	mAP/%	Rank-1/%
1.0	88.6	94.1	43.9	69.0
2.0	88.9	94.4	43.1	68.8
3.0	89.4	95.0	44.3	69.5
4.0	89.0	94.8	43.0	68.1

Tab. 5 Influence of loss weight on model precision

参数 $ω$	Market-1501		MSMT17
参数 $ω$	mAP/%	Rank-1/%	mAP/%	Rank-1/%
0.0	88.2	94.2	40.9	66.4
0.1	89.0	94.5	41.2	67.0
0.2	89.1	94.8	41.8	67.2
0.3	89.0	94.6	42.6	67.8
0.4	89.0	94.4	43.8	68.7
0.5	89.4	95.0	44.3	69.5
0.6	89.2	94.4	43.0	68.1
0.7	89.3	94.4	42.8	68.0
0.8	89.2	94.6	42.4	67.7
0.9	89.2	94.3	41.8	67.3
1.0	89.0	94.3	41.5	67.0

Tab. 5 Influence of loss weight on model precision

参数 $ω$	Market-1501		MSMT17
参数 $ω$	mAP/%	Rank-1/%	mAP/%	Rank-1/%
0.0	88.2	94.2	40.9	66.4
0.1	89.0	94.5	41.2	67.0
0.2	89.1	94.8	41.8	67.2
0.3	89.0	94.6	42.6	67.8
0.4	89.0	94.4	43.8	68.7
0.5	89.4	95.0	44.3	69.5
0.6	89.2	94.4	43.0	68.1
0.7	89.3	94.4	42.8	68.0
0.8	89.2	94.6	42.4	67.7
0.9	89.2	94.3	41.8	67.3
1.0	89.0	94.3	41.5	67.0

Fig. 2 t-SNE visualization results of model trained by baseline method

Fig. 3 t-SNE visualization results of model trained by proposed method

Fig. 4 Retrieval visualization results of proposed method

Fig. 5 Heatmap visualization results of different methods

References 51

1	何嘉明，杨巨成，吴超，等. 基于多模态图卷积神经网络的行人重识别方法［J］. 计算机应用， 2023， 43（7）： 2182-2189.
	HE J M， YANG J C， WU C， et al. Person re-identification method based on multi-modal graph convolutional neural network ［J］. Journal of Computer Applications， 2023， 43（7）： 2182-2189.
2	陈代丽，许国良. 基于注意力机制学习域内变化的跨域行人重识别方法［J］. 计算机应用， 2022， 42（5）： 1391-1397.
	CHEN D L， XU G L. Cross-domain person re-identification method based on attention mechanism with learning intra-domain variance ［J］. Journal of Computer Applications， 2022， 42（5）： 1391-1397.
3	姚英茂，姜晓燕. 基于图卷积网络与自注意力图池化的视频行人重识别方法［J］. 计算机应用， 2023， 43（3）： 728-735.
	YAO Y M， JIANG X Y. Video-based person re-identification method based on graph convolution network and self-attention graph pooling［J］. Journal of Computer Applications， 2023， 43（3）： 728-735.
4	PENG J， JIANG G， WANG H. Adaptive memorization with group labels for unsupervised person re-identification ［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2023， 33（10）： 5802-5813.
5	CHEN F， WANG N， TANG J， et al. Unsupervised person re-identification via multi-domain joint learning ［J］. Pattern Recognition， 2023， 138： No.109369.
6	LAN L， TENG X， ZHANG J， et al. Learning to purification for unsupervised person re-identification ［J］. IEEE Transactions on Image Processing， 2023， 32： 3338-3353.
7	FAN H， ZHENG L， YAN C， et al. Unsupervised person re-identification： clustering and fine-tuning ［J］. ACM Transactions on Multimedia Computing， Communications， and Applications， 2018， 14（4）： No.83.
8	HE K， ZHANG X， REN S， et al. Deep residual learning for image recognition ［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2016： 770-778.
9	LLOYD S. Least squares quantization in PCM ［J］. IEEE Transactions on Information Theory， 1982， 28（2）： 129-137.
10	ESTER M， KRIEGEL H P， SANDER J， et al. A density-based algorithm for discovering clusters in large spatial databases with noise ［C］// Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining. Palo Alto： AAAI Press， 1996： 226-231.
11	DOSOVITSKIY A， BEYER L， KOLESNIKOV A， et al. An image is worth 16x16 words： Transformers for image recognition at scale［EB/OL］. （2021-06-03）［2023-06-13］. .
12	FU Y， WEI Y， WANG G， et al. Self-similarity grouping： a simple unsupervised cross domain adaptation approach for person re-identification ［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 6111-6120.
13	GE Y， CHEN D， LI H. Mutual mean-teaching： pseudo label refinery for unsupervised domain adaptation on person re-identification ［EB/OL］. （2020-01-30）［2023-05-12］. .
14	GE Y， ZHU F， CHEN D， et al. Self-paced contrastive learning with hybrid memory for domain adaptive object re-ID ［C］// Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2020： 11309-11321.
15	DAI Z， WANG G， YUAN W， et al. Cluster contrast for unsupervised person re-identification ［C］// Proceedings of the 2022 Asian Conference on Computer Vision， LNCS 13846. Cham： Springer， 2023： 319-337.
16	HU Z， ZHU C， HE G. Hard-sample guided hybrid contrast learning for unsupervised person re-identification ［C］// Proceedings of the 7th IEEE International Conference on Network Intelligence and Digital Content. Piscataway： IEEE， 2021： 91-95.
17	LAI S， CHAI Z， WEI X. Transformer meets part model： adaptive part division for person re-identification ［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision Workshops. Piscataway： IEEE， 2021： 4133-4140.
18	SUN Y， ZHENG L， YANG Y， et al. Beyond part models： person retrieval with refined part pooling （and a strong convolutional baseline）［C］// Proceedings of the 2018 European Conference on Computer Vision， LNCS 11208. Cham： Springer， 2018： 501-518.
19	WANG G， YUAN Y， CHEN X， et al. Learning discriminative features with multiple granularities for person re-identification［C］// Proceedings of the 26th ACM International Conference on Multimedia. New York： ACM， 2018： 274-282.
20	ZHANG G， ZHANG P， QI J， et al. HAT： hierarchical aggregation Transformers for person re-identification ［C］// Proceedings of the 29th ACM International Conference on Multimedia. New York： ACM， 2021： 516-525.
21	LI Y， HE J， ZHANG T， et al. Diverse part discovery： occluded person re-identification with part-aware Transformer ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 2897-2906.
22	HE S， LUO H， WANG P， et al. TransReID： Transformer-based object re-identification ［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2021： 14993-15002.
23	LIAO S， SHAO L. TransMatcher： deep image matching through Transformers for generalizable person re-identification ［C］// Proceedings of the 35th International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2021： 1992-2003.
24	NI H， LI Y， GAO L， et al. Part-aware Transformer for generalizable person re-identification ［C］// Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2023： 11246-11255.
25	ZHU K， GUO H， ZHANG S， et al. AAformer： auto-aligned Transformer for person re-identification ［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2023（Early Access）： 1-11.
26	LUO H， WANG P， XU Y， et al. Self-supervised pre-training for Transformer-based person re-identification ［EB/OL］. （2021-11-23）［2023-06-13］. .
27	KRIZHEVSKY A， SUTSKEVER I， HINTON G E. ImageNet classification with deep convolutional neural networks ［C］// Proceedings of the 25th International Conference on Neural Information Processing Systems — Volume 1. Red Hook： Curran Associates Inc.， 2012： 1097-1105.
28	FU D， CHEN D， BAO J， et al. Unsupervised pre-training for person re-identification ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 14745-14754.
29	TAO Y， ZHANG J， CHEN T， et al. Transformer-based contrastive learning for unsupervised person re-identification ［C］// Proceedings of the 2022 International Joint Conference on Neural Networks. Piscataway： IEEE， 2022： 1-9.
30	D’ASCOLI S， TOUVRON H， LEAVITT M L， et al. ConViT： improving vision Transformers with soft convolutional inductive biases ［C］// Proceedings of the 38th International Conference on Machine Learning. New York： JMLR.org， 2021： 2286-2296.
31	SUKHBAATAR S， GRAVE E， BOJANOWSKI P， et al. Adaptive attention span in Transformers ［C］// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2019： 331-335.
32	TOUVRON H， CORD M， DOUZE M， et al. Training data-efficient image Transformers & distillation through attention ［C］// Proceedings of the 38th International Conference on Machine Learning. New York： JMLR.org， 2021： 10347-10357.
33	HINTON G， VINYALS O， DEAN J. Distilling the knowledge in a neural network ［EB/OL］. （2015-03-09）［2023-07-09］. .
34	ZHANG L， SONG J， GAO A， et al. Be your own teacher： improve the performance of convolutional neural networks via self distillation ［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 3712-3721.
35	YUN S， PARK J， LEE K， et al. Regularizing class-wise predictions via self-knowledge distillation ［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 13873-13882.
36	WANG Y， LI H， CHAU L P， et al. Embracing the dark knowledge： domain generalization using regularized knowledge distillation ［C］// Proceedings of the 29th ACM International Conference on Multimedia. New York： ACM， 2021： 2595-2604.
37	SULTANA M， NASEER M， KHAN M H， et al. Self-distilled vision Transformer for domain generalization ［C］// Proceedings of the 2022 Asian Conference on Computer Vision， LNCS 13842. Cham： Springer， 2023： 273-290.
38	CHEN X， FAN H， GIRSHICK R， et al. Improved baselines with momentum contrastive learning ［EB/OL］. （2020-03-09）［2024-03-23］. .
39	ZHENG L， SHEN L， TIAN L， et al. Scalable person re-identification： a benchmark ［C］// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2015： 1116-1124.
40	WEI L， ZHANG S， GAO W， et al. Person transfer GAN to bridge domain gap for person re-identification ［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 79-88.
41	WANG D， ZHANG S. Unsupervised person re-identification via multi-label classification ［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 10978-10987.
42	ZHENG K， LAN C， ZENG W， et al. Exploiting sample uncertainty for domain adaptive person re-identification ［C］// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2021： 3538-3546.
43	LIN Y， DONG X， ZHENG L， et al. A bottom-up clustering approach to unsupervised person re-identification ［C］// Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2019： 8738-8745.
44	LIN Y， XIE L， WU Y， et al. Unsupervised person re-identification via softened similarity learning ［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 3387-3396.
45	ZENG K， NING M， WANG Y， et al. Hierarchical clustering with hard-batch triplet loss for person re-identification ［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 13654-13662.
46	WANG Z， ZHANG J， ZHENG L， et al. CycAs： self-supervised cycle association for learning re-identifiable descriptions ［C］// Proceedings of the 2020 European Conference on Computer Vision， LNCS 12356. Cham： Springer， 2020： 72-88.
47	WU J， LIU H， YANG Y， et al. Unsupervised graph association for person re-identification ［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 8320-8329.
48	ZHONG Z， ZHENG L， LUO Z， et al. Invariance matters： exemplar memory for domain adaptive person re-identification［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2019： 598-607.
49	LI M， ZHU X， GONG S. Unsupervised person re-identification by deep learning tracklet association ［C］// Proceedings of the 2018 European Conference on Computer Vision， LNCS 11208. Cham： Springer， 2018： 772-788.
50	VAN DER MAATEN L， HINTON G. Visualizing data using t-SNE［J］. Journal of Machine Learning Research， 2008， 9： 2579-2605.
51	SELVARAJU R R， COGSWELL M， DAS A， et al. Grad-CAM： visual explanations from deep networks via gradient-based localization ［C］// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2017： 618-626.

[1]	Yubo ZHAO, Liping ZHANG, Sheng YAN, Min HOU, Mao GAO. Relation extraction between discipline knowledge entities based on improved piecewise convolutional neural network and knowledge distillation [J]. Journal of Computer Applications, 2024, 44(8): 2421-2429.
[2]	Cui WANG, Miaolei DENG, Dexian ZHANG, Lei LI, Xiaoyan YANG. Review of end-to-end person search algorithms based on images [J]. Journal of Computer Applications, 2024, 44(8): 2544-2550.
[3]	Xiawuji, Heming HUANG, Gengzangcuomao, Yutao FAN. Survey of extractive text summarization based on unsupervised learning and supervised learning [J]. Journal of Computer Applications, 2024, 44(4): 1035-1048.
[4]	Rong HUANG, Junjie SONG, Shubo ZHOU, Hao LIU. Image aesthetic quality evaluation method based on self-supervised vision Transformer [J]. Journal of Computer Applications, 2024, 44(4): 1269-1276.
[5]	Zongze JIA, Pengfei GAO, Yinglong MA, Xiaofeng LIU, Haixin XIA. Multi-feature fusion attention-based hierarchical classification method for dialogue act [J]. Journal of Computer Applications, 2024, 44(3): 715-721.
[6]	Xue LI, Guangle YAO, Honghui WANG, Jun LI, Haoran ZHOU, Shaoze YE. Remote sensing image classification based on sample incremental learning [J]. Journal of Computer Applications, 2024, 44(3): 732-736.
[7]	Rui JIANG, Wei LIU, Cheng CHEN, Tao LU. Asymmetric unsupervised end-to-end image deraining network [J]. Journal of Computer Applications, 2024, 44(3): 922-930.
[8]	Yuxin HUANG, Yiwang HUANG, Hui HUANG. Meta label correction method based on shallow network predictions [J]. Journal of Computer Applications, 2024, 44(11): 3364-3370.
[9]	Pei ZHAO, Yan QIAO, Rongyao HU, Xinyu YUAN, Minyue LI, Benchu ZHANG. Multivariate time series anomaly detection based on multi-domain feature extraction [J]. Journal of Computer Applications, 2024, 44(11): 3419-3426.
[10]	Nengbing HU, Biao CAI, Xu LI, Danhua CAO. Graph classification method based on graph pooling contrast learning [J]. Journal of Computer Applications, 2024, 44(11): 3327-3334.
[11]	Fu LIN, Jiasheng SHI, Ze GAO, Zunkang CHU, Qiongmin MA, Haiyan YU, Weixiong RAO. Physical system simulation based on deep representation learning for 3D geometric features [J]. Journal of Computer Applications, 2024, 44(11): 3548-3555.
[12]	Wen ZHOU, Yuzhang CHEN, Zhiyuan WEN, Shiqi WANG. Fish image classification based on positional overlapping patch embedding and multi-scale channel interactive attention [J]. Journal of Computer Applications, 2024, 44(10): 3209-3216.
[13]	Xujian ZHAO, Hanglin LI. Deep neural network compression algorithm based on hybrid mechanism [J]. Journal of Computer Applications, 2023, 43(9): 2686-2691.
[14]	Zhangjian JI, Ming ZHANG, Zilong WANG. High-precision object detection algorithm based on improved VarifocalNet [J]. Journal of Computer Applications, 2023, 43(7): 2147-2154.
[15]	Menglin HUANG, Lei DUAN, Yuanhao ZHANG, Peiyan WANG, Renhao LI. Prompt learning based unsupervised relation extraction model [J]. Journal of Computer Applications, 2023, 43(7): 2010-2016.

Unsupervised person re-identification based on self-distilled vision Transformer

基于自蒸馏视觉Transformer的无监督行人重识别

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 51

Related Articles 15

Recommended Articles

Metrics