Yizhi Luo
Research Subjects
Yizhi Luo has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Hang Zou
China Telecom Research Institute, Beijing, China
2 shared publications - Huan Liu
Beijing Jiaotong University
2 shared publications - Xueli Hu
Key Laboratory of Cyberspace Security, Ministry of Education, Zhengzhou, China
2 shared publications - Yuan Zhang
China Telecom Research Institute, Beijing, China
2 shared publications - Bo Zhao
School of Cyber Science and Engineering, Wuhan University, Wuhan, China
1 shared publication - Haocheng Yuan
Macau University of Science and Technology, Macau, China
1 shared publication
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9171-9182
Towards Event-Aware Forecasting in DeFi: Insights from On-chain Automated Market Maker Protocols
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9171-9182
Open AccessTowards Event-Aware Forecasting in DeFi: Insights from On-chain Automated Market Maker Protocols
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 994-1003
Style-conditional Prompt Token Learning for Generalizable Face Anti-spoofing
Face anti-spoofing (FAS) based on domain generalization (DG) has attracted increasing attention from researchers. The reason for the poor generalization is that the model is overfitted to salient liveness-irrelevant signals. However, the previous methods alleviate the overfitting by mapping the images from multiple domains into a common feature space or promoting the separation of image features from domain-specific features and task-related features. If the text features of vision-language pre-trained (VLP) models (e.g., CLIP) are used to dynamically adjust the image features to gain a better generalization, we can not only explore a wider feature space but also avoid the potential degradation of semantic information. Specifically, we propose a FAS method of Style-Conditional Prompt Token Learning (S-CPTL), which aims to generate generalized text features by training the introduced prompt tokens to carry visual styles and use them as weights for classifiers to improve the model's generalization. Compared to the inherently static prompt token, we propose the dynamic prompt token, which can adaptively capture live-irrelevant signals from the instance-specific styles and increase their diversity through mixed feature statistics to further reduce the overfitting of the model. Thorough experimental analysis demonstrates that S-CPTL exceeds current top-performing methods in four distinct cross-dataset benchmarks.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 994-1003
Open AccessStyle-conditional Prompt Token Learning for Generalizable Face Anti-spoofing
Face anti-spoofing (FAS) based on domain generalization (DG) has attracted increasing attention from researchers. The reason for the poor generalization is that the model is overfitted to salient liveness-irrelevant signals. However, the previous methods alleviate the overfitting by mapping the images from multiple domains into a common feature space or promoting the separation of image features from domain-specific features and task-related features. If the text features of vision-language pre-trained (VLP) models (e.g., CLIP) are used to dynamically adjust the image features to gain a better generalization, we can not only explore a wider feature space but also avoid the potential degradation of semantic information. Specifically, we propose a FAS method of Style-Conditional Prompt Token Learning (S-CPTL), which aims to generate generalized text features by training the introduced prompt tokens to carry visual styles and use them as weights for classifiers to improve the model's generalization. Compared to the inherently static prompt token, we propose the dynamic prompt token, which can adaptively capture live-irrelevant signals from the instance-specific styles and increase their diversity through mixed feature statistics to further reduce the overfitting of the model. Thorough experimental analysis demonstrates that S-CPTL exceeds current top-performing methods in four distinct cross-dataset benchmarks.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 7619-7628
Fine-Grained Prompt Learning for Face Anti-Spoofing
There has been an increasing focus on domain-generalized (DG) face anti-spoofing (FAS). However, existing methods aim to project a shared visual space through adversarial training, making exploring the space without losing semantic information challenging. We investigate the DG inadequacies resulting from classifier overfitting to a significantly different domain distribution. To address this issue, we propose a novel Fine-Grained Prompt Learning (FGPL) based on Vision-Language Models (VLMs), such as CLIP, which can adaptively adjust weights for classifiers with text features to mitigate overfitting. Specifically, FGPL first motivates the prompts to learn content and domain semantic information by capturing Domain-Agnostic and Domain-Specific features. Furthermore, our prompts are designed to be category-generalized by diversifying the Domain-Specific prompts. Additionally, we design an Adaptive Convolutional Adapter (AC-adapter), which is implemented through an adaptive combination of Vanilla Convolution and Central Difference Convolution, to be inserted into the image encoder for quickly bridging the gap between general image recognition and FAS task. Extensive experiments demonstrate that the proposed FGPL is effective and outperforms state-of-the-art methods on several cross-domain datasets.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 7619-7628
Open AccessFine-Grained Prompt Learning for Face Anti-Spoofing
There has been an increasing focus on domain-generalized (DG) face anti-spoofing (FAS). However, existing methods aim to project a shared visual space through adversarial training, making exploring the space without losing semantic information challenging. We investigate the DG inadequacies resulting from classifier overfitting to a significantly different domain distribution. To address this issue, we propose a novel Fine-Grained Prompt Learning (FGPL) based on Vision-Language Models (VLMs), such as CLIP, which can adaptively adjust weights for classifiers with text features to mitigate overfitting. Specifically, FGPL first motivates the prompts to learn content and domain semantic information by capturing Domain-Agnostic and Domain-Specific features. Furthermore, our prompts are designed to be category-generalized by diversifying the Domain-Specific prompts. Additionally, we design an Adaptive Convolutional Adapter (AC-adapter), which is implemented through an adaptive combination of Vanilla Convolution and Central Difference Convolution, to be inserted into the image encoder for quickly bridging the gap between general image recognition and FAS task. Extensive experiments demonstrate that the proposed FGPL is effective and outperforms state-of-the-art methods on several cross-domain datasets.