While successful for various computer vision tasks, deep neural networks have shown to be vulnerable to texture style shifts and small perturbations to which humans are robust. In this work, we show that the robustness of neural networks can be greatly improved through the use of random convolutions as data augmentation. Random convolutions are approximately shape-preserving and may distort local textures. Intuitively, randomized convolutions create an infinite number of new domains with similar global shapes but random local textures. Therefore, we explore using outputs of multi-scale random convolutions as new images or mixing them with the original images during training. When applying a network trained with our approach to unseen domains, our method consistently improves the performance on domain generalization benchmarks and is scalable to ImageNet. In particular, in the challenging scenario of generalizing to the sketch domain in PACS and to ImageNet-Sketch, our method outperforms state-of-art methods by a large margin. More interestingly, our method can benefit downstream tasks by providing a more robust pretrained visual representation.
Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning
The University of Hong Kong（香港大学）；Shanghai AI Lab（上海人工智能实验室）；Peking University（北京大学）；Tsinghua University（清华大学）；Shanghai Qi Zhi Institute（上海期智研究院）；Shanghai Jiao Tong University（上海交通大学）
Towards Generalizable Deepfake Detection via Forgery-aware Audio-Visual Adaptation: A Variational Bayesian Approach
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Department of New Networks, Pengcheng Laboratory（鹏城实验室网络部）；School of Cyber Science and Technology, Sun Yat-sen University（中山大学网络安全科学与技术学院）；School of Computer Science and Cyber Engineering, Guangzhou University（广州大学计算机科学与网络工程学院）；School of Cyberspace Science, Harbin Institute of Technology（哈尔滨工业大学网络空间科学学院）
Do You See What I Say? Generalizable Deepfake Detection based on Visual Speech Recognition
Machine Intelligence Group, Department of CS&IS, Birla Institute of Technology and Sciences, Pilani, India（机器智能组，计算机科学与信息系，比拉理工学院和科学学院，比拉，印度）；STARS team Inria Center at Université Côte d’Azur in Sophia Antipolis, France（法国索菲亚Antipolis大学的Inria中心的STARS团队）
Scale-Aware Pre-Training for Human-Centric Visual Perception: Enabling Lightweight and Generalizable Models
Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China（深圳先进研究院，电子科学与技术大学）；Center for Future Media, University of Electronic Science and Technology of China（未来媒体中心，电子科学与技术大学）；TongJi University（同济大学）
Beyond Semantic Priors: Mitigating Optimization Collapse for Generalizable Visual Forensics
Institute of Information Engineering, Chinese Academy of Sciences（信息工程研究所，中国科学院）；School of Cyber Science and Technology, Beihang University（北京航空航天大学信息与科学学院）
Sparse Mixture-of-Experts are Domain Generalizable Learners
Nanyang Technological University（南洋理工大学）；The Hong Kong University of Science and Technology（香港科技大学）；Mila-Quebec AI Institute（米拉-魁北克人工智能研究所）；Nvidia Research（英伟达研究院）
Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction
School of Informatics, Xiamen University（厦门大学信息学院）；Huawei（华为）；Aginome Scientific（Aginome科技公司）；Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属胸科医院）
针对 WSI 分类中粗粒度语义监督不足和高分辨率计算开销问题，提出 FiVE 框架，通过细粒度病理语义交互、TFS 模块和实例子集采样提升泛化能力。
Generalizable Image Repair for Robust Visual Control
University of Florida AI Scholars Program（佛罗里达大学人工智能学者计划）；Trustworthy Engineered Autonomy (TEA) Lab（可信工程自主性实验室）；Department of Electrical and Computer Engineering（电气与计算机工程系）
Harnessing Foundation Models for Robust and Generalizable 6-DOF Bronchoscopy Localization
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；The First Affiliated Hospital, Sun Yat-sen University（中山大学第一附属医院）；Centre for Artificial Intelligence and Robotics, Chinese Academy of Sciences, HK, China（中国科学院香港人工智能与机器人中心）；School of Engineering and Imaging Sciences, King’s College London, UK（伦敦国王学院工程与影像科学学院）
HANS-Net: Hyperbolic Convolution and Adaptive Temporal Attention for Accurate and Generalizable Liver and Tumor Segmentation in CT Imaging
Department of Computer Science and Engineering, United International University（计算机科学与工程系，国际大学）；Faculty of Science and Technology, Charles Darwin University（科学与技术学院，查尔斯达尔文大学）；Faculty of Science and Information Technology, Charles Darwin University（科学与信息技术学院，查尔斯达尔文大学）
MFVLR: Multi-domain Fine-grained Vision-Language Reconstruction for Generalizable Diffusion Face Forgery Detection and Localization
Faculty of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences)（计算机科学与技术学院，齐鲁工业大学（山东省科学院））；School of Computing, National University of Singapore（国立新加坡大学计算机学院）；Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences)（山东省人工智能研究院，齐鲁工业大学（山东省科学院））；Key Laboratory of Computer Vision and System, Ministry of Education, Tianjin University of Technology（教育部计算机视觉与系统重点实验室，天津工业大学）
