1 code implementation • 21 Sep 2024 • Haoran Zhang, Shuanghao Bai, Wanqi Zhou, Jingwen Fu, Badong Chen
In this work, we propose Prompt-Driven Text Adapter (PromptTA) method, which is designed to better capture the distribution of style features and employ resampling to ensure thorough coverage of domain knowledge.
1 code implementation • 14 May 2024 • Wanqi Zhou, Shuanghao Bai, Shujian Yu, Qibin Zhao, Badong Chen
With the advancement of neural networks, diverse methods for neural Granger causality have emerged, which demonstrate proficiency in handling complex data, and nonlinear relationships.
1 code implementation • 30 Apr 2024 • Wanqi Zhou, Shuanghao Bai, Danilo P. Mandic, Qibin Zhao, Badong Chen
To this end, this work presents the first comprehensive study on improving the adversarial robustness of VLMs against attacks targeting image, text, and multimodal inputs.
1 code implementation • 30 Apr 2024 • Shuanghao Bai, Yuedi Zhang, Wanqi Zhou, Zhirong Luan, Badong Chen
During the inference phase, the generator of the generative model is employed to obtain instance-specific soft prompts for the unseen target domain.
Ranked #3 on
Domain Generalization
on VLCS
1 code implementation • 15 Dec 2023 • Shuanghao Bai, Wanqi Zhou, Zhirong Luan, Donglin Wang, Badong Chen
Multilayer perceptron (MLP) has shown its capability to learn transferable representations in various downstream tasks, such as unsupervised image classification and supervised concept generalization.
Ranked #3 on
Cross-Domain Few-Shot
on ChestX
1 code implementation • 15 Dec 2023 • Shuanghao Bai, Min Zhang, Wanqi Zhou, Siteng Huang, Zhirong Luan, Donglin Wang, Badong Chen
Therefore, in this paper, we first experimentally demonstrate that the unsupervised-trained VLMs can significantly reduce the distribution discrepancy between source and target domains, thereby improving the performance of UDA.
Ranked #3 on
Unsupervised Domain Adaptation
on Office-31