Yifan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yifan Wang has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Ran Song
School of Control Science and Engineering, Shandong University, Jinan, China
4 shared publications - Lin Zhang
School of Control Science and Engineering, Shandong University, Jinan, China
3 shared publications - Paul L. Rosin
Cardiff University, Cardiff, United Kingdom
3 shared publications - Wei Zhang
Shandong University
3 shared publications - Hongliang Li
University of Electronic Science and Technology of China
2 shared publications - Lin Zhang
Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA
2 shared publications
Latest Publications
- 30 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 9564-9574
Neighborhood-Aware Mutual Information Maximization for Source-Free Domain Adaptation
Recently, the source-free domain adaptation (SFDA) problem has attracted much attention, where the pre-trained model for the source domain is adapted to the target domain in the absence of source data. However, due to domain shift, the negative alignment usually exists between samples from the same class, which may lower intra-class feature similarity. To address this issue, we present a self-supervised representation learning strategy for SFDA, named as neighborhood-aware mutual information (NAMI), which maximizes the mutual information (MI) between the representations of target samples and their corresponding neighbors. Moreover, we theoretically demonstrate that NAMI can be decomposed into a weighted sum of local MI, which suggests that the weighted terms can better estimate NAMI. To this end, we introduce neighborhood consensus score over the set of weakly and strongly augmented views and point-wise density based on neighborhood, both of which determine the weights of local MI for NAMI by leveraging the neighborhood information of samples. The proposed method can significantly handle domain shift and adaptively reduce the noise in the neighborhood of each target sample. In combination with the consistency loss over views, NAMI leads to consistent improvement over existing state-of-the-art methods on three popular SFDA benchmarks.
- 30 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 9564-9574
Neighborhood-Aware Mutual Information Maximization for Source-Free Domain Adaptation
Recently, the source-free domain adaptation (SFDA) problem has attracted much attention, where the pre-trained model for the source domain is adapted to the target domain in the absence of source data. However, due to domain shift, the negative alignment usually exists between samples from the same class, which may lower intra-class feature similarity. To address this issue, we present a self-supervised representation learning strategy for SFDA, named as neighborhood-aware mutual information (NAMI), which maximizes the mutual information (MI) between the representations of target samples and their corresponding neighbors. Moreover, we theoretically demonstrate that NAMI can be decomposed into a weighted sum of local MI, which suggests that the weighted terms can better estimate NAMI. To this end, we introduce neighborhood consensus score over the set of weakly and strongly augmented views and point-wise density based on neighborhood, both of which determine the weights of local MI for NAMI by leveraging the neighborhood information of samples. The proposed method can significantly handle domain shift and adaptively reduce the noise in the neighborhood of each target sample. In combination with the consistency loss over views, NAMI leads to consistent improvement over existing state-of-the-art methods on three popular SFDA benchmarks.
- 3 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 16 (4) , 1352-1363
Dual-Graph Contrastive Learning for Unsupervised Person Reidentification
Unsupervised person re-identification (re-ID) aims to perform person retrieval in an unsupervised manner across multiple cameras. Most recent works usually adopted contrastive learning with clustering strategy to guide learning process. However, the domain gap between cameras easily causes the high intra-class variance and prohibits an effective contrastive learning. To overcome this problem, we propose dual-graph contrastive learning (Dual-GCL) to fully utilize the structures between the instances as well as the relationship between the instances and the centroids generated by the clustering strategy. Firstly, a dual-graph is constructed by utilizing the affinities of instances in the feature space and the pseudo-label space derived from clustering strategy with the node-to-node contrastive learning. Then, to capture the relations between the dual-graph and the centroids, we perform dual-graph contrastive learning at both the node level and the super-node level. The contrastive learning based on the two levels can encode multi-level structural representations between the instances corresponding to the nodes in dual-graph and align the centroids between different cameras in the shared embedding space. Moreover, a camera-aware augmentation scheme that exploits the semantic relationship is proposed to alleviate the domain discrepancy between cameras. Experimental results demonstrate that our approach outperforms the state-of-the-art methods.
- 3 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 16 (4) , 1352-1363
Dual-Graph Contrastive Learning for Unsupervised Person Reidentification
Unsupervised person re-identification (re-ID) aims to perform person retrieval in an unsupervised manner across multiple cameras. Most recent works usually adopted contrastive learning with clustering strategy to guide learning process. However, the domain gap between cameras easily causes the high intra-class variance and prohibits an effective contrastive learning. To overcome this problem, we propose dual-graph contrastive learning (Dual-GCL) to fully utilize the structures between the instances as well as the relationship between the instances and the centroids generated by the clustering strategy. Firstly, a dual-graph is constructed by utilizing the affinities of instances in the feature space and the pseudo-label space derived from clustering strategy with the node-to-node contrastive learning. Then, to capture the relations between the dual-graph and the centroids, we perform dual-graph contrastive learning at both the node level and the super-node level. The contrastive learning based on the two levels can encode multi-level structural representations between the instances corresponding to the nodes in dual-graph and align the centroids between different cameras in the shared embedding space. Moreover, a camera-aware augmentation scheme that exploits the semantic relationship is proposed to alleviate the domain discrepancy between cameras. Experimental results demonstrate that our approach outperforms the state-of-the-art methods.
- 8 December 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (5) , 1800-1816
Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation
- 8 December 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (5) , 1800-1816
Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation
- Open Access
Provably Uncertainty-Guided Universal Domain Adaptation
Universal domain adaptation (UniDA) aims to transfer the knowledge from a labeled source domain to an unlabeled target domain without any assumptions of the label sets, which requires distinguishing the unknown samples from the known ones in the target domain. A main challenge of UniDA is that the nonidentical label sets cause the misalignment between the two domains. Moreover, the domain discrepancy and the supervised objectives in the source domain easily lead the whole model to be biased towards the common classes and produce overconfident predictions for unknown samples. To address the above challenging problems, we propose a new uncertainty-guided UniDA framework. Firstly, we introduce an empirical estimation of the probability of a target sample belonging to the unknown class which fully exploits the distribution of the target samples in the latent space. Then, based on the estimation, we propose a novel neighbors searching scheme in a linear subspace with a $\delta$-filter to estimate the uncertainty score of a target sample and discover unknown samples. It fully utilizes the relationship between a target sample and its neighbors in the source domain to avoid the influence of domain misalignment. Secondly, this paper well balances the confidences of predictions for both known and unknown samples through an uncertainty-guided margin loss based on the confidences of discovered unknown samples, which can reduce the gap between the intra-class variances of known classes with respect to the unknown class. Finally, experiments on three public datasets demonstrate that our method significantly outperforms existing state-of-the-art methods.
Open AccessProvably Uncertainty-Guided Universal Domain Adaptation
Universal domain adaptation (UniDA) aims to transfer the knowledge from a labeled source domain to an unlabeled target domain without any assumptions of the label sets, which requires distinguishing the unknown samples from the known ones in the target domain. A main challenge of UniDA is that the nonidentical label sets cause the misalignment between the two domains. Moreover, the domain discrepancy and the supervised objectives in the source domain easily lead the whole model to be biased towards the common classes and produce overconfident predictions for unknown samples. To address the above challenging problems, we propose a new uncertainty-guided UniDA framework. Firstly, we introduce an empirical estimation of the probability of a target sample belonging to the unknown class which fully exploits the distribution of the target samples in the latent space. Then, based on the estimation, we propose a novel neighbors searching scheme in a linear subspace with a $\delta$-filter to estimate the uncertainty score of a target sample and discover unknown samples. It fully utilizes the relationship between a target sample and its neighbors in the source domain to avoid the influence of domain misalignment. Secondly, this paper well balances the confidences of predictions for both known and unknown samples through an uncertainty-guided margin loss based on the confidences of discovered unknown samples, which can reduce the gap between the intra-class variances of known classes with respect to the unknown class. Finally, experiments on three public datasets demonstrate that our method significantly outperforms existing state-of-the-art methods.
- Open Access
Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation
Universal domain adaptation (UniDA) aims to transfer the knowledge of common classes from the source domain to the target domain without any prior knowledge on the label set, which requires distinguishing in the target domain the unknown samples from the known ones. Recent methods usually focused on categorizing a target sample into one of the source classes rather than distinguishing known and unknown samples, which ignores the inter-sample affinity between known and unknown samples and may lead to suboptimal performance. Aiming at this issue, we propose a novel UDA framework where such inter-sample affinity is exploited. Specifically, we introduce a knowability-based labeling scheme which can be divided into two steps: 1) Knowability-guided detection of known and unknown samples based on the intrinsic structure of the neighborhoods of samples, where we leverage the first singular vectors of the affinity matrices to obtain the knowability of every target sample. 2) Label refinement based on neighborhood consistency to relabel the target samples, where we refine the labels of each target sample based on its neighborhood consistency of predictions. Then, auxiliary losses based on the two steps are used to reduce the inter-sample affinity between the unknown and the known target samples. Finally, experiments on four public datasets demonstrate that our method significantly outperforms existing state-of-the-art methods.
Open AccessExploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation
Universal domain adaptation (UniDA) aims to transfer the knowledge of common classes from the source domain to the target domain without any prior knowledge on the label set, which requires distinguishing in the target domain the unknown samples from the known ones. Recent methods usually focused on categorizing a target sample into one of the source classes rather than distinguishing known and unknown samples, which ignores the inter-sample affinity between known and unknown samples and may lead to suboptimal performance. Aiming at this issue, we propose a novel UDA framework where such inter-sample affinity is exploited. Specifically, we introduce a knowability-based labeling scheme which can be divided into two steps: 1) Knowability-guided detection of known and unknown samples based on the intrinsic structure of the neighborhoods of samples, where we leverage the first singular vectors of the affinity matrices to obtain the knowability of every target sample. 2) Label refinement based on neighborhood consistency to relabel the target samples, where we refine the labels of each target sample based on its neighborhood consistency of predictions. Then, auxiliary losses based on the two steps are used to reduce the inter-sample affinity between the unknown and the known target samples. Finally, experiments on four public datasets demonstrate that our method significantly outperforms existing state-of-the-art methods.
- 30 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 41 (8) , 2598-2610
MFS: A Brain-Inspired Memory Formation System for GAN
Generative adversarial networks (GANs) are subject to catastrophic forgetting when learning stream of data. Inspired by the knowledge of neuroscience, this article develops a memory formation system (MFS) to establish memory for GANs. MFS is composed of three modules, including the identifier, weights upgrade (WU), and weights reactivate (WR). These modules simulate the function of encoding, consolidating, and retrieving in memory formation of human. Identifier creates indexes to label continuous tasks and these indexes are used as a cue when the corresponding tasks are recalled. WU and WR work as synaptic consolidation and system consolidation, respectively. In WU, a novel method, weight saliency measure (WSM) is proposed to measure the saliency of weight. Valuable weights are protected and invaluable weights are released for update when GAN is trained for the new task. In WR, traditional data-replay methods are improved by selecting ${k}$ representatives in each class and their feature vectors are restored. When pseudo data of this class are regenerated, only the samples with distance less than a threshold can be used in future training. Experimental results based on the testing of continual image generation and continual 3-D reconstruction show that MFS can establish a memory system to handle the catastrophic forgetting problem effectively.
- 30 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 41 (8) , 2598-2610
MFS: A Brain-Inspired Memory Formation System for GAN
Generative adversarial networks (GANs) are subject to catastrophic forgetting when learning stream of data. Inspired by the knowledge of neuroscience, this article develops a memory formation system (MFS) to establish memory for GANs. MFS is composed of three modules, including the identifier, weights upgrade (WU), and weights reactivate (WR). These modules simulate the function of encoding, consolidating, and retrieving in memory formation of human. Identifier creates indexes to label continuous tasks and these indexes are used as a cue when the corresponding tasks are recalled. WU and WR work as synaptic consolidation and system consolidation, respectively. In WU, a novel method, weight saliency measure (WSM) is proposed to measure the saliency of weight. Valuable weights are protected and invaluable weights are released for update when GAN is trained for the new task. In WR, traditional data-replay methods are improved by selecting ${k}$ representatives in each class and their feature vectors are restored. When pseudo data of this class are regenerated, only the samples with distance less than a threshold can be used in future training. Experimental results based on the testing of continual image generation and continual 3-D reconstruction show that MFS can establish a memory system to handle the catastrophic forgetting problem effectively.
- 14 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 509-514
Design of a New Intelligent City Bus System
Nowadays, the city bus system develops rapidly, but there are still many problems in the current bus system that affects people’s travel convenience and safety of life and property. To solve the problems in the bus system, in this paper, a new urban bus system is proposed by combining intelligent sensor equipment and wireless communication technology. This bus system can realize passenger detection, bus door to prevent accidental clamping, driver’s health monitoring, bus dynamic space allocation, real-time feedback of bus information and other functions. Besides, passengers can get access to the bus real-time information to reasonably plan their travel mode and travel route. Therefore, people’s travel accessibility, punctuality and safety are increased. Considering the travel of the disabled, this paper also proposes automated barrier-free ramp, voice prompts and other functions so that the disabled can also benefit the convenience brought by urban development.
- 14 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 509-514
Design of a New Intelligent City Bus System
Nowadays, the city bus system develops rapidly, but there are still many problems in the current bus system that affects people’s travel convenience and safety of life and property. To solve the problems in the bus system, in this paper, a new urban bus system is proposed by combining intelligent sensor equipment and wireless communication technology. This bus system can realize passenger detection, bus door to prevent accidental clamping, driver’s health monitoring, bus dynamic space allocation, real-time feedback of bus information and other functions. Besides, passengers can get access to the bus real-time information to reasonably plan their travel mode and travel route. Therefore, people’s travel accessibility, punctuality and safety are increased. Considering the travel of the disabled, this paper also proposes automated barrier-free ramp, voice prompts and other functions so that the disabled can also benefit the convenience brought by urban development.
- 1 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 217-221
Structure Consistency and Class Discriminative Feature Learning for Heterogeneous Domain Adaptation
Heterogeneous domain adaptation (HDA), which learns a target classifier using labeled data from different feature and distribution, has shown promising value in knowledge discovery. Yet it is still a challenging problem. Since most of the existing approaches for HDA are in the special case, we propose a generalized method for this problem. We use Principal Components Analysis (PCA) to align the features from source and target domain. Simultaneously, we match the conditional distribution and preserve the local structure, for the purpose of achieving discriminative feature representations. At last, comprehensive experiments verify that our method can significantly outperform state-of-the-art learning methods on several public image datasets.
- 1 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 217-221
Structure Consistency and Class Discriminative Feature Learning for Heterogeneous Domain Adaptation
Heterogeneous domain adaptation (HDA), which learns a target classifier using labeled data from different feature and distribution, has shown promising value in knowledge discovery. Yet it is still a challenging problem. Since most of the existing approaches for HDA are in the special case, we propose a generalized method for this problem. We use Principal Components Analysis (PCA) to align the features from source and target domain. Simultaneously, we match the conditional distribution and preserve the local structure, for the purpose of achieving discriminative feature representations. At last, comprehensive experiments verify that our method can significantly outperform state-of-the-art learning methods on several public image datasets.