Jianwen Gan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jianwen Gan has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Hang Zou
China Telecom Research Institute, Beijing, China
1 shared publication - Haocheng Yuan
Macau University of Science and Technology, Macau, China
1 shared publication - Huan Liu
Beijing Jiaotong University
1 shared publication - Ning Zhang
Institute of Forensic Science, Ministry of Public Security, Beijing 100038, China
1 shared publication - Xueli Hu
Key Laboratory of Cyberspace Security, Ministry of Education, Zhengzhou, China
1 shared publication - Yizhi Luo
Sichuan Intelligent Transportation System Management Co., Ltd., Chengdu, China
1 shared publication
Latest Publications
- 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.