Fan Zhou
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
Research Subjects
Fan Zhou has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Boyu Wang
Western University
6 shared publications - Changjian Shui
Vector Institute, Toronto, ON, Canada
4 shared publications - Christian Gagné
Université Laval, Québec, Canada
4 shared publications - Shichun Yang
Beihang University
4 shared publications - Charles X. Ling
Western University
3 shared publications Boyu Wang
Department of Computer Science, Western University, 1151 Richmond St, London, N6A 3K7, Ontario, Canada; Vector Institute, Toronto, 661 University Ave Suite 710, M5G 1M1, Ontario, Canada
2 shared publications
Latest Publications
- 6 March 2025
- Published by Elsevier in Neural Networks
- Vol. 187, 107275
FedELR: When federated learning meets learning with noisy labels
- 6 March 2025
- Published by Elsevier in Neural Networks
- Vol. 187, 107275
FedELR: When federated learning meets learning with noisy labels
- 11 December 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 266
Enhancing road surface recognition via optimal transport and metric learning in task-agnostic intelligent driving environments
- 11 December 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 266
Enhancing road surface recognition via optimal transport and metric learning in task-agnostic intelligent driving environments
- 26 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (11) , 6385-6396
Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning
Continual learning aims to learn a series of tasks sequentially without forgetting the knowledge acquired from the previous ones. In this work, we propose the Hessian Aware Low-Rank Perturbation algorithm for continual learning. By modeling the parameter transitions along the sequential tasks with the weight matrix transformation, we propose to apply the low-rank approximation on the task-adaptive parameters in each layer of the neural networks. Specifically, we theoretically demonstrate the quantitative relationship between the Hessian and the proposed low-rank approximation. The approximation ranks are then globally determined according to the marginal change of the empirical loss estimated by the layer-specific gradient and low-rank approximation error. Furthermore, we control the model capacity by pruning less important parameters to diminish the parameter growth. We conduct extensive experiments on various benchmarks, including a dataset with large-scale tasks, and compare our method against some recent state-of-the-art methods to demonstrate the effectiveness and scalability of our proposed method. Empirical results show that our method performs better on different benchmarks, especially in achieving task order robustness and handling the forgetting issue.
- 26 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (11) , 6385-6396
Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning
Continual learning aims to learn a series of tasks sequentially without forgetting the knowledge acquired from the previous ones. In this work, we propose the Hessian Aware Low-Rank Perturbation algorithm for continual learning. By modeling the parameter transitions along the sequential tasks with the weight matrix transformation, we propose to apply the low-rank approximation on the task-adaptive parameters in each layer of the neural networks. Specifically, we theoretically demonstrate the quantitative relationship between the Hessian and the proposed low-rank approximation. The approximation ranks are then globally determined according to the marginal change of the empirical loss estimated by the layer-specific gradient and low-rank approximation error. Furthermore, we control the model capacity by pruning less important parameters to diminish the parameter growth. We conduct extensive experiments on various benchmarks, including a dataset with large-scale tasks, and compare our method against some recent state-of-the-art methods to demonstrate the effectiveness and scalability of our proposed method. Empirical results show that our method performs better on different benchmarks, especially in achieving task order robustness and handling the forgetting issue.
- 13 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (10) , 10140-10150
Towards More General Loss and Setting in Unsupervised Domain Adaptation
In this article, we present an analysis of unsupervised domain adaptation with a series of theoretical and algorithmic results. We derive a novel Rényi-$\alpha$ divergence-based generalization bound, which is tailored to domain adaptation algorithms with arbitrary loss functions in a stochastic setting. Moreover, our theoretical results provide new insights into the assumptions for successful domain adaptation: the closeness between the conditional distributions of the domains and the Lipschitzness on the source domain. With these assumptions, we reveal the following: if their conditional generation distributions are close, the Lipschitzness property of the target domain can be transferred from the Lipschitzness on the source domain, without knowing the exact target distribution. Motivated by our analysis and assumptions, we further derive practical principles for deep domain adaptation: 1) Rényi-2 adversarial training for marginal distributions matching and 2) Lipschitz regularization for the classifier. Our experimental results on both synthetic and real-world datasets support our theoretical findings and the practical efficiency of the proposed principles.- 13 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (10) , 10140-10150
Towards More General Loss and Setting in Unsupervised Domain Adaptation
In this article, we present an analysis of unsupervised domain adaptation with a series of theoretical and algorithmic results. We derive a novel Rényi-$\alpha$ divergence-based generalization bound, which is tailored to domain adaptation algorithms with arbitrary loss functions in a stochastic setting. Moreover, our theoretical results provide new insights into the assumptions for successful domain adaptation: the closeness between the conditional distributions of the domains and the Lipschitzness on the source domain. With these assumptions, we reveal the following: if their conditional generation distributions are close, the Lipschitzness property of the target domain can be transferred from the Lipschitzness on the source domain, without knowing the exact target distribution. Motivated by our analysis and assumptions, we further derive practical principles for deep domain adaptation: 1) Rényi-2 adversarial training for marginal distributions matching and 2) Lipschitz regularization for the classifier. Our experimental results on both synthetic and real-world datasets support our theoretical findings and the practical efficiency of the proposed principles.- 29 March 2023
- Published by Elsevier in Neural Networks
- Vol. 163, 244-255
On the value of label and semantic information in domain generalization
- 29 March 2023
- Published by Elsevier in Neural Networks
- Vol. 163, 244-255
On the value of label and semantic information in domain generalization
- 24 February 2023
- Published by Elsevier in Neural Networks
- Vol. 162, 34-45
Episodic task agnostic contrastive training for multi-task learning
- 24 February 2023
- Published by Elsevier in Neural Networks
- Vol. 162, 34-45
Episodic task agnostic contrastive training for multi-task learning
- 24 November 2022
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 90, 103706
Attention-adaptive multi-scale feature aggregation dehazing network
- 24 November 2022
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 90, 103706
Attention-adaptive multi-scale feature aggregation dehazing network
- 9 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3273-3278
Temporal-aware Mechanism with Bidirectional Complementarity for Video Q&A
Video question answering (Video Q&A) is a challenging task as it requires a sufficient understanding of the video and question information. Video is composed of frame sequence, which contains multi-scale temporal relationships and corresponding contextual information. A model competently tackle Video Q&A task that needs to be able to: 1) construct long-term and neighborhood dependencies in frame sequences to extract global and local contextual features that can reflect multi-scale temporal dependencies, and deduce the temporal-aware refined features, and 2) identify static and dynamic features from pertinent moments of a video, while filtering away question-irrelated dependencies of feature sequences, to yield the most precise and reasonable temporal-aware overall contextual features. In response to the above requirements, we propose a novel Video Q&A mechanism which consists of Bidirectional Complementary Attention(BCA) module and Adaptive Temporal-aware(ATA) module. Bidirectional complementary attention module stacks multi-head self-attention layer and convolutional layer in different orders to designed two kinds of attention units, which is able to make bidirectional multi-step reasoning based on complete global information and accurate local information to obtain temporal-aware refined features. Adaptive temporal-aware module is used to filter away question-irrelated dependencies in the feature sequence to yield the most precise and reasonable temporal-aware overall contextual features. Comprehensive comparative experiments are conducted on publicly available benchmark datasets. An extended ablation study is further conducted to show the usefulness of each module of the solution in acquiring its computational Q&A capabilities.
- 9 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3273-3278
Temporal-aware Mechanism with Bidirectional Complementarity for Video Q&A
Video question answering (Video Q&A) is a challenging task as it requires a sufficient understanding of the video and question information. Video is composed of frame sequence, which contains multi-scale temporal relationships and corresponding contextual information. A model competently tackle Video Q&A task that needs to be able to: 1) construct long-term and neighborhood dependencies in frame sequences to extract global and local contextual features that can reflect multi-scale temporal dependencies, and deduce the temporal-aware refined features, and 2) identify static and dynamic features from pertinent moments of a video, while filtering away question-irrelated dependencies of feature sequences, to yield the most precise and reasonable temporal-aware overall contextual features. In response to the above requirements, we propose a novel Video Q&A mechanism which consists of Bidirectional Complementary Attention(BCA) module and Adaptive Temporal-aware(ATA) module. Bidirectional complementary attention module stacks multi-head self-attention layer and convolutional layer in different orders to designed two kinds of attention units, which is able to make bidirectional multi-step reasoning based on complete global information and accurate local information to obtain temporal-aware refined features. Adaptive temporal-aware module is used to filter away question-irrelated dependencies in the feature sequence to yield the most precise and reasonable temporal-aware overall contextual features. Comprehensive comparative experiments are conducted on publicly available benchmark datasets. An extended ablation study is further conducted to show the usefulness of each module of the solution in acquiring its computational Q&A capabilities.
- 24 September 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 257
A novel domain adaptation theory with Jensen–Shannon divergence
- 24 September 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 257
A novel domain adaptation theory with Jensen–Shannon divergence
- 18 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 13, 1-6
Multi-Target Domain Transfer Detector on Bad Weather Conditions
With the popularization of object detection in fields such as autonomous driving and surveillance, object detection networks are required to be used in more changeable scenarios. However, a multi-target domain adaptive object detection network is a challenging problem. Due to the lack of relevant datasets and the limitation of traditional domain adaptive methods, there is a lack of pertinent research in this field. Traditional single-target domain adaptive methods are often ineffective when used in multi-target domain adaptive problems. To allow the object detection network to be applied to multiple target domains, we propose the “domain transfer module” and the “multi-scale hybrid attention domain alignment module”. At the same time, we synthesized the “BlendedCityspce” dataset for training and testing of a multi-target domain adaptive target object network. The network provided in this paper has a good performance in the multi-target domain adaptation and reaches the state-of-the-art in the single-target domain adaptation. You can find our source code in https://github.com/Chonghuan-Liu/Multi-Target-Domain-Adaptative-Detector.
- 18 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 13, 1-6
Multi-Target Domain Transfer Detector on Bad Weather Conditions
With the popularization of object detection in fields such as autonomous driving and surveillance, object detection networks are required to be used in more changeable scenarios. However, a multi-target domain adaptive object detection network is a challenging problem. Due to the lack of relevant datasets and the limitation of traditional domain adaptive methods, there is a lack of pertinent research in this field. Traditional single-target domain adaptive methods are often ineffective when used in multi-target domain adaptive problems. To allow the object detection network to be applied to multiple target domains, we propose the “domain transfer module” and the “multi-scale hybrid attention domain alignment module”. At the same time, we synthesized the “BlendedCityspce” dataset for training and testing of a multi-target domain adaptive target object network. The network provided in this paper has a good performance in the multi-target domain adaptation and reaches the state-of-the-art in the single-target domain adaptation. You can find our source code in https://github.com/Chonghuan-Liu/Multi-Target-Domain-Adaptative-Detector.