no code implementations • 22 May 2024 • Zhendong Liu, Yuanbi Nie, Yingshui Tan, Xiangyu Yue, Qiushi Cui, Chongjun Wang, Xiaoyong Zhu, Bo Zheng
To address this issue, we enhance the existing VLMs' visual modality safety alignment by adding safety modules, including a safety projector, safety tokens, and a safety head, through a two-stage training process, effectively improving the model's defense against risky images.
no code implementations • 30 Apr 2024 • Zhendong Liu, Haifeng Xia, Tong Guo, Libo Sun, Ming Shao, Siyu Xia
In addition, a dedicated temporal convolution is applied at each level to learn short-term temporal features, which will be carried over from shallow to deep layers to maximize the leverage of low-level details.
no code implementations • 7 Sep 2023 • Zhendong Liu, Jie Zhang, Qiangqiang He, Chongjun Wang
In the realm of visual recognition, data augmentation stands out as a pivotal technique to amplify model robustness.
no code implementations • 8 Dec 2022 • Zhendong Liu, Wenyu Jiang, Min Guo, Chongjun Wang
Based on the analysis of the internal mechanisms, we develop a mask-based boosting method for data augmentation that comprehensively improves several robustness measures of AI models and beats state-of-the-art data augmentation approaches.
no code implementations • 1 Aug 2021 • Zhendong Liu, Van Manh, Xin Yang, Xiaoqiong Huang, Karim Lekadir, Víctor Campello, Nishant Ravikumar, Alejandro F Frangi, Dong Ni
A style transfer model with style fusion is employed to generate the curriculum samples.
no code implementations • 11 Jan 2021 • Zhendong Liu, Xiaoqiong Huang, Xin Yang, Rui Gao, Rui Li, Yuanji Zhang, Yankai Huang, Guangquan Zhou, Yi Xiong, Alejandro F Frangi, Dong Ni
Deep segmentation models that generalize to images with unknown appearance are important for real-world medical image analysis.
no code implementations • 24 Sep 2020 • Xiaoqiong Huang, Zejian Chen, Xin Yang, Zhendong Liu, Yuxin Zou, Mingyuan Luo, Wufeng Xue, Dong Ni
Based on the zero-shot style transfer to remove appearance shift and test-time augmentation to explore diverse underlying anatomy, our proposed method is effective in combating the appearance shift.
no code implementations • 14 Feb 2020 • Zhendong Liu, Xin Yang, Rui Gao, Shengfeng Liu, Haoran Dou, Shuangchi He, Yuhao Huang, Yankai Huang, Huanjia Luo, Yuanji Zhang, Yi Xiong, Dong Ni
In this paper, we propose a novel and intuitive framework to remove the appearance shift, and hence improve the generalization ability of DNNs.