Hybrid Contrastive Learning for Unsupervised Person Re-Identification

Si, Tongzhen; He, Fazhi; Zhang, Zhong; Duan, Yun‐Bo

doi:10.1109/tmm.2022.3174414

Cited by 68 publications

(6 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the transferability of the proposed method, it is possible and efficient to transfer the agent trained in lower resolution data to the reconstruction of higher resolution. In addition, we will extend our work with other advanced learning methods for fast learning, such as parallel computing [83], neural dynamic classification algorithm [84], dynamic ensemble learning algorithm [85], finite element machine [86], and contrastive learning [87,88]. Moreover, since the actions defined in this paper can be executed by CAD software, the CAD software can be used as an environment to interact with agents.…”

Section: Discussionmentioning

confidence: 99%

3D reconstruction based on hierarchical reinforcement learning with transferability

Fan

et al. 2023

ICA

Self Cite

View full text Add to dashboard Cite

3D reconstruction is extremely important in CAD (computer-aided design)/CAE (computer-aided Engineering)/CAM (computer-aided manufacturing). For interpretability, reinforcement learning (RL) is used to reconstruct 3D shapes from images by a series of editing actions. However, typical applications of RL for 3D reconstruction face problems. The search space will increase exponentially with the action space due to the curse of dimensionality, which leads to low performance, especially for complex action spaces in 3D reconstruction. Additionally, most works involve training a specific agent for each shape class without learning related experiences from others. Therefore, we present a hierarchical RL approach with transferability to reconstruct 3D shapes (HRLT3D). First, actions are grouped into macro actions that can be chosen by the top-agent. Second, the task is accordingly decomposed into hierarchically simplified sub-tasks solved by sub-agents. Different from classical hierarchical RL (HRL), we propose a sub-agent based on augmented state space (ASS-Sub-Agent) to replace a set of sub-agents, which can speed up the training process due to shared learning and having fewer parameters. Furthermore, the ASS-Sub-Agent is more easily transferred to data of other classes due to the augmented diverse states and the simplified tasks. The experimental results on typical public dataset show that the proposed HRLT3D performs overwhelmingly better than recent baselines. More impressingly, the experiments also demonstrate the extreme transferability of our approach among data of different classes.

show abstract

Section: Discussionmentioning

confidence: 99%

3D reconstruction based on hierarchical reinforcement learning with transferability

Fan

et al. 2023

ICA

Self Cite

View full text Add to dashboard Cite

show abstract

“…We divided the purely unsupervised methods into two categories based on whether camera labels were used or not. Most of these camera-agnostic methods, including BUC [12], RLCC [47], HCM [71], PPLR [21], Cluster-Contrast [13], exploit robust clustering methods to generate accurate labels and design effective strategies to reduce label noise. Without camera information, it is difficult for them to cope with the label noise caused by camera domain shifts.…”

Section: B Comparison With the State-of-the-art Methodsmentioning

confidence: 99%

Camera-Aware Style Separation and Contrastive Learning for Unsupervised Person Re-Identification

Liang

Jin

et al. 2022

2022 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

Unsupervised person re-identification aims to retrieve images of a specified person without identity labels. Many recent unsupervised Re-ID approaches adopt clustering-based methods to measure cross-camera feature similarity to roughly divide images into clusters. They ignore the feature distribution discrepancy induced by camera domain gap, resulting in the unavoidable performance degradation. Camera information is usually available, and the feature distribution in the single camera usually focuses more on the appearance of the individual and has less intra-identity variance. Inspired by the observation, we introduce a Camera-Aware Label Refinement (CALR) framework that reduces camera discrepancy by clustering intracamera similarity. Specifically, we employ intra-camera training to obtain reliable local pseudo labels within each camera, and then refine global labels generated by inter-camera clustering and train the discriminative model using more reliable global pseudo labels in a self-paced manner. Meanwhile, we develop a cameraalignment module to align feature distributions under different cameras, which could help deal with the camera variance further. Extensive experiments validate the superiority of our proposed method over state-of-the-art approaches. The code is accessible at https://github.com/leeBooMla/CALR.

show abstract

“…State-of-the-art unsupervised person Re-ID is based on clustering methods [23][24][25]. Many techniques have been offered to improve the estimation of pseudo-labels.…”

Section: Related Work 21 Unsupervised Person Re-idmentioning

confidence: 99%

UnA-Mix: Rethinking Image Mixtures for Unsupervised Person Re-Identification

Liu,

Sun,

Liu

et al. 2024

Processes

View full text Add to dashboard Cite

With the development of ultra-long-range visual sensors, the application of unsupervised person re-identification algorithms to them has become increasingly important. However, these algorithms inevitably generate noisy pseudo-labels, which seriously hinder the performance of tasks over a large range. Mixup, a data enhancement technique, has been validated in supervised learning for its generalization to noisy labels. Based on this observation, to our knowledge, this study is the first to explore the impact of the mixup technique on unsupervised person re-identification, which is a downstream task of contrastive learning, in detail. Specifically, mixup was applied in different locations (at the pixel level and feature level) in an unsupervised person re-identification framework to explore its influences on task performance. In addition, based on the richness of the information contained in the person samples to be mixed, we propose an uncertainty-aware mixup (UnA-Mix) method, which reduces the over-learning of simple person samples and avoids the information damage that occurs when information-rich person samples are mixed. The experimental results on three benchmark person re-identification datasets demonstrated the applicability of the proposed method, especially on the MSMT17, where it outperformed state-of-the-art methods by 5.2% and 4.8% in terms of the mAP and rank-1, respectively.

show abstract

Hybrid Contrastive Learning for Unsupervised Person Re-Identification

Cited by 68 publications

References 57 publications

3D reconstruction based on hierarchical reinforcement learning with transferability

3D reconstruction based on hierarchical reinforcement learning with transferability

Camera-Aware Style Separation and Contrastive Learning for Unsupervised Person Re-Identification

UnA-Mix: Rethinking Image Mixtures for Unsupervised Person Re-Identification

Contact Info

Product

Resources

About