Yi Li
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
Yi Li has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Dazhong Rong
College of Computer Science and Technology, Zhejiang University, Hangzhou, China
2 shared publications Neeraj Suri
Lancaster University
2 shared publications- Neeraj Suri
School of Computing and Communications, Lancaster University, Lancaster, U.K.
2 shared publications Plamen Angelov
Lancaster University
2 shared publications- Plamen Angelov
School of Computing and Communications, Lancaster University, Lancaster, UK
2 shared publications - Syed Mohsen Naqvi
Intelligent Sensing and Communication Group, School of Engineering, Newcastle University, Newcastle upon Tyne, U.K.
2 shared publications
Latest Publications
- RetractionOpen Access
- 10 October 2025
- Published by Springer Nature
- p. C1
Retraction Note to: CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Ground Image Synthesis
- 10 October 2025
- Published by Springer Nature
- p. C1
RetractionOpen AccessRetraction Note to: CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Ground Image Synthesis
- 26 November 2024
- Published by Springer Nature
- p. 236-252
Self-supervised Representation Learning for Adversarial Attack Detection
- 26 November 2024
- Published by Springer Nature
- p. 236-252
Self-supervised Representation Learning for Adversarial Attack Detection
- 3 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 32 (12) , 7015-7024
Adversarial Attack Detection via Fuzzy Predictions
Image processing using neural networks act as a tool to speed up predictions for users, specifically on large-scale image samples. To guarantee the clean data for training accuracy, various deep learning-based adversarial attack detection techniques have been proposed. These crisp set-based detection methods directly determine whether an image is clean or attacked, while, calculating the loss is non-differentiable and hinders training through normal back-propagation. Motivated by the recent success in fuzzy systems, in this work, we present an attack detection method to further improve detection performance, which is suitable for any pre-trained neural network classifier. Subsequently, the fuzzification network is used to obtain feature maps to produce fuzzy sets of difference degree between clean and attacked images. The fuzzy rules control the intelligence that determines the detection boundaries. Different from previous fuzzy systems, we propose a fuzzy mean-intelligence mechanism with new support and confidence functions to improve fuzzy rule's quality. In the defuzzification layer, the fuzzy prediction from the intelligence is mapped back into the crisp model predictions for images. The loss between the prediction and label controls the rules to train the fuzzy detector. We show that the fuzzy rule-based network learns rich feature information than binary outputs and offer to obtain an overall performance gain. Experiment results show that compared to various benchmark fuzzy systems and adversarial attack detection methods, our fuzzy detector achieves better detection performance over a wide range of images.
- 3 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 32 (12) , 7015-7024
Adversarial Attack Detection via Fuzzy Predictions
Image processing using neural networks act as a tool to speed up predictions for users, specifically on large-scale image samples. To guarantee the clean data for training accuracy, various deep learning-based adversarial attack detection techniques have been proposed. These crisp set-based detection methods directly determine whether an image is clean or attacked, while, calculating the loss is non-differentiable and hinders training through normal back-propagation. Motivated by the recent success in fuzzy systems, in this work, we present an attack detection method to further improve detection performance, which is suitable for any pre-trained neural network classifier. Subsequently, the fuzzification network is used to obtain feature maps to produce fuzzy sets of difference degree between clean and attacked images. The fuzzy rules control the intelligence that determines the detection boundaries. Different from previous fuzzy systems, we propose a fuzzy mean-intelligence mechanism with new support and confidence functions to improve fuzzy rule's quality. In the defuzzification layer, the fuzzy prediction from the intelligence is mapped back into the crisp model predictions for images. The loss between the prediction and label controls the rules to train the fuzzy detector. We show that the fuzzy rule-based network learns rich feature information than binary outputs and offer to obtain an overall performance gain. Experiment results show that compared to various benchmark fuzzy systems and adversarial attack detection methods, our fuzzy detector achieves better detection performance over a wide range of images.
- 17 September 2024
- Published by Springer Nature
- p. 159-173
Federated Adversarial Learning for Robust Autonomous Landing Runway Detection
- 17 September 2024
- Published by Springer Nature
- p. 159-173
Federated Adversarial Learning for Robust Autonomous Landing Runway Detection
- Retracted
- 17 September 2024
- Published by Springer Nature
- p. 287-302
RETRACTED CHAPTER: CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Ground Image Synthesis
- 17 September 2024
- Published by Springer Nature
- p. 287-302
RetractedRETRACTED CHAPTER: CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Ground Image Synthesis
- Open Access
Self-Supervised Representation Learning for Adversarial Attack Detection
Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised representation learning framework for the adversarial attack detection task to address this drawback. Firstly, we map the pixels of augmented input images into an embedding space. Then, we employ the prototype-wise contrastive estimation loss to cluster prototypes as latent variables. Additionally, drawing inspiration from the concept of memory banks, we introduce a discrimination bank to distinguish and learn representations for each individual instance that shares the same or a similar prototype, establishing a connection between instances and their associated prototypes. We propose a parallel axial-attention (PAA)-based encoder to facilitate the training process by parallel training over height- and width-axis of attention maps. Experimental results show that, compared to various benchmark self-supervised vision learning models and supervised adversarial attack detection methods, the proposed model achieves state-of-the-art performance on the adversarial attack detection task across a wide range of images.
Open AccessSelf-Supervised Representation Learning for Adversarial Attack Detection
Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised representation learning framework for the adversarial attack detection task to address this drawback. Firstly, we map the pixels of augmented input images into an embedding space. Then, we employ the prototype-wise contrastive estimation loss to cluster prototypes as latent variables. Additionally, drawing inspiration from the concept of memory banks, we introduce a discrimination bank to distinguish and learn representations for each individual instance that shares the same or a similar prototype, establishing a connection between instances and their associated prototypes. We propose a parallel axial-attention (PAA)-based encoder to facilitate the training process by parallel training over height- and width-axis of attention maps. Experimental results show that, compared to various benchmark self-supervised vision learning models and supervised adversarial attack detection methods, the proposed model achieves state-of-the-art performance on the adversarial attack detection task across a wide range of images.
- 12 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 31 (23299290) , 1511-1521
U-Shaped Transformer With Frequency-Band Aware Attention for Speech Enhancement
Recently, Transformer shows the potential to exploit the long-range sequence dependency in speech with self-attention. It has been introduced in single channel speech enhancement to improve the accuracy of speech estimation from a noise mixture. However, the amount of information represented across attention-heads is often huge, which leads to increased computational complexity. To address this issue, the axial attention is proposed i.e., to split a 2D attention into two 1-D attentions. In this paper, we develop a new method for speech enhancement by leveraging the axial attention, where we generate time and frequency sub-attention maps by calculating the attention map along time- and frequency-axis. Different from the conventional axial attention, the proposed method provides two parallel multi-head attentions for time- and frequency-axis, respectively. Moreover, the frequency-band aware attention is proposed i.e., high frequency-band attention (HFA), and low frequency-band attention (LFA), which facilitates the exploitation of the information related to speech and noise in different frequency bands in the noisy mixture. To re-use high-resolution feature maps from the encoder, we design a U-shaped Transformer, which helps recover lost information from the high-level representations to further improve the speech estimation accuracy. Extensive experiments on four public datasets are used to demonstrate the efficacy of the proposed method. The code of the proposed method is available at https://github.com/Yukino-3/U-shaped-Transformer-SE .
- 12 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 31 (23299290) , 1511-1521
U-Shaped Transformer With Frequency-Band Aware Attention for Speech Enhancement
Recently, Transformer shows the potential to exploit the long-range sequence dependency in speech with self-attention. It has been introduced in single channel speech enhancement to improve the accuracy of speech estimation from a noise mixture. However, the amount of information represented across attention-heads is often huge, which leads to increased computational complexity. To address this issue, the axial attention is proposed i.e., to split a 2D attention into two 1-D attentions. In this paper, we develop a new method for speech enhancement by leveraging the axial attention, where we generate time and frequency sub-attention maps by calculating the attention map along time- and frequency-axis. Different from the conventional axial attention, the proposed method provides two parallel multi-head attentions for time- and frequency-axis, respectively. Moreover, the frequency-band aware attention is proposed i.e., high frequency-band attention (HFA), and low frequency-band attention (LFA), which facilitates the exploitation of the information related to speech and noise in different frequency bands in the noisy mixture. To re-use high-resolution feature maps from the encoder, we design a U-shaped Transformer, which helps recover lost information from the high-level representations to further improve the speech estimation accuracy. Extensive experiments on four public datasets are used to demonstrate the efficacy of the proposed method. The code of the proposed method is available at https://github.com/Yukino-3/U-shaped-Transformer-SE .
- 20 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 3 (1) , 43-52
Domain Adaptation and Autoencoder-Based Unsupervised Speech Enhancement
As a category of transfer learning, domain adaptation plays an important role in generalizing the model trained in one task and applying it to other similar tasks or settings. In speech enhancement, a well-trained acoustic model can be exploited to obtain the speech signal in the context of other languages, speakers, and environments. Recent domain-adaptation research was developed more effectively with various neural networks and high-level abstract features. However, the related studies are more likely to transfer the well-trained model from a rich and more diverse domain to a limited and similar domain. Therefore, in this article, the domain-adaptation method is proposed in unsupervised speech enhancement for the opposite circumstance, that is, transferring to a larger and richer domain. On the one hand, the importance-weighting (IW) approach is exploited with a variance-constrained autoencoder to reduce the shift of shared weights between the source and target domains. On the other hand, in order to train the classifier with the worst-case weights and minimize the risk, the minimax method is proposed. Both the proposed IW and minimax methods are evaluated from the VOICE BANK and IEEE datasets to the TIMIT dataset. The experimental results show that the proposed methods outperform the state-of-the-art approaches.
- 20 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 3 (1) , 43-52
Domain Adaptation and Autoencoder-Based Unsupervised Speech Enhancement
As a category of transfer learning, domain adaptation plays an important role in generalizing the model trained in one task and applying it to other similar tasks or settings. In speech enhancement, a well-trained acoustic model can be exploited to obtain the speech signal in the context of other languages, speakers, and environments. Recent domain-adaptation research was developed more effectively with various neural networks and high-level abstract features. However, the related studies are more likely to transfer the well-trained model from a rich and more diverse domain to a limited and similar domain. Therefore, in this article, the domain-adaptation method is proposed in unsupervised speech enhancement for the opposite circumstance, that is, transferring to a larger and richer domain. On the one hand, the importance-weighting (IW) approach is exploited with a variance-constrained autoencoder to reduce the shift of shared weights between the source and target domains. On the other hand, in order to train the classifier with the worst-case weights and minimize the risk, the minimax method is proposed. Both the proposed IW and minimax methods are evaluated from the VOICE BANK and IEEE datasets to the TIMIT dataset. The experimental results show that the proposed methods outperform the state-of-the-art approaches.