Partially Recentralization Softmax Loss for Vision-Language Models Robustness
部分重校正softmax损失用于视觉-语言模型鲁棒性
Hao Wang, Jinzhe Jiang, Xin Zhang, Chen Li
专题命中
图文多模态
:multimodal(abstract);分类 cs.CL、cs.AI
AI总结
本文提出部分重校正softmax损失,通过限制top K softmax输出提升预训练多模态模型的对抗鲁棒性,实验显示细调后模型对主流攻击更具鲁棒性。
CommentsThe study described in Section 4 was conducted without required institutional review board approval. The paper is withdrawn pending completion of the approval process
Zikang Liu, Longteng Guo, Handong Li, Ru Zhen, Xingjian He, Ruyi Ji, Xiaoming Ren, Yanhao Zhang, Haonan Lu, Jing Liu
机构
*
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
;
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
;
OPPO AI Center, OPPO Inc.(OPPO人工智能中心,OPPO公司)
CommentsThere are some writing errors in our methods section that need to be corrected. We will then add extensive experiments and rewrite the Introduction and related work sections
机构
*
School of Software Engineering, Xi’an Jiaotong University(西安交通大学软件工程学院)
;
School of Computer Science and Information Engineering, Hefei University of Technology(合肥工业大学计算机科学与信息工程学院)
;
CSIRO(澳大利亚联邦科学与工业研究组织)
;
Northwestern Polytechnical University(西北工业大学)
;
University of Macau(澳门大学)
Multiscale Structure-Guided Latent Diffusion for Multimodal MRI Translation
多尺度结构引导的潜在扩散模型用于多模态MRI翻译
Jianqiang Lin, Zhiqiang Shen, Peng Cao, Jinzhu Yang, Osmar R. Zaiane, Xiaoli Liu
机构
*
Computer Science and Engineering, Northeastern University, Shenyang, China(东北大学计算机科学与工程系,沈阳,中国)
;
Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education, Northeastern University, Shenyang, China(教育部医学图像智能计算重点实验室,东北大学,沈阳,中国)
;
National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Shenyang, China(工业智能与系统优化国家级前沿科学中心,沈阳,中国)
;
Amii, University of Alberta, Edmonton, Alberta, Canada(阿尔伯塔大学阿米人工智能研究所,埃德蒙顿,阿尔伯塔,加拿大)
;
AiShiWeiLai AI Research, Beijing, China(人工智能研究(北京)有限公司,北京,中国)