Classifiers trained on given databases perform poorly when tested on data acquired in different settings. This is explained in domain adaptation through a shift among distributions of the source and target domains. Attempts to align them have traditionally resulted in works reducing the domain shift by introducing appropriate loss terms, measuring the discrepancies between source and target distributions, in the objective function. Here we take a different route, proposing to align the learned representations by embedding in any given network specific Domain Alignment Layers, designed to match the source and target feature distributions to a reference one. Opposite to previous works which define a priori in which layers adaptation should be performed, our method is able to automatically learn the degree of feature alignment required at different levels of the deep network. Thorough experiments on different public benchmarks, in the unsupervised setting, confirm the power of our approach.
Automatic Registration of SHG and H&E Images with Feature-based Initial Alignment and Intensity-based Instance Optimization: Contribution to the COMULIS Challenge
AGH University of Krakow(克拉科夫AGH科技大学);University of Applied Sciences Western Switzerland (HES-SO Valais-Wallis)(瑞士西部应用科学大学(瓦莱州-瓦利斯));University of Geneva(日内瓦大学)
A Semi-automatic Cranial Implant Design Tool Based on Rigid ICP Template Alignment and Voxel Space Reconstruction
Institute for Artificial Intelligence in Medicine, University Hospital Essen (AöR)(埃森大学医院人工智能医学研究所);Institute of Computer Graphics and Vision, Graz University of Technology(格拉茨技术大学计算机图形学与视觉研究所);University Hospital RWTH Aachen(亚琛工业大学医院);Institute of Medical Informatics, University Hospital RWTH Aachen(亚琛工业大学医院医学信息学研究所)
Ultrasound Report Generation with Cross-Modality Feature Alignment via Unsupervised Guidance
Technical University of Munich(慕尼黑工业大学);Munich Center for Machine Learning(慕尼黑机器学习中心);Shenzhen Institute of Advanced Technology, the Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Chair for Computer Aided Medical Procedures and Augmented Reality (CAMP), Technical University of Munich(慕尼黑工业大学计算机辅助医疗程序与增强现实教席);The Third Medical Centre of Chinese PLA General Hospital(中国人民解放军总医院第三医学中心);The Second School of Clinical Medicine, Southern Medical University(南方医科大学第二临床医学院)
Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval
Beijing University of Posts and Telecommunications(北京邮电大学);SenseTime(商汤科技);Beijing Key Laboratory of Network System and Network Culture(北京网络系统与网络文化重点实验室);Key Laboratory of Intereactive Technology and Experience System, Ministry of Culture and Tourism(文化和旅游部交互技术与体验系统重点实验室)
ViT3D Alignment of LLaMA3: 3D Medical Image Report Generation
School of Electronic Engineering and Computer Science, Queen Mary University of London(伦敦玛丽女王大学电子工程与计算机科学学院);Department of Bioengineering, Imperial College London(伦敦帝国理工学院生物工程系);Meta Inc.(Meta公司);School of Engineering, College of Engineering and Physical Sciences, University of Birmingham(伯明翰大学工程学院、工程与物理科学学院)
Training-free image style alignment for self-adapting domain shift on handheld ultrasound devices
School of Information Science and Technology, ShanghaiTech University(上海科技大学信息科学与技术学院);Shanghai Advanced Research Institute, Chinese Academy of Sciences(中国科学院上海高等研究院);University of Chinese Academy of Sciences(中国科学院大学);College of Computer Science, Sichuan University(四川大学计算机学院);College of Intelligence and Computing, Tianjin University(天津大学智能与计算学部);The Chinese University of Hong Kong(香港中文大学);Beth Israel Deaconess Medical Center, Harvard Medical School(哈佛医学院贝斯以色列女执事医疗中心);Institute of High Performance Computing, Agency for Science, Technology and Research(新加坡科技研究局高性能计算研究所)