In this paper, a unified approach is presented to transfer learning that addresses several source and target domain label-space and annotation assumptions with a single model. It is particularly effective in handling a challenging case, where source and target label-spaces are disjoint, and outperforms alternatives in both unsupervised and semi-supervised settings. The key ingredient is a common representation termed Common Factorised Space. It is shared between source and target domains, and trained with an unsupervised factorisation loss and a graph-based loss. With a wide range of experiments, we demonstrate the flexibility, relevance and efficacy of our method, both in the challenging cases with disjoint label spaces, and in the more conventional cases such as unsupervised domain adaptation, where the source and target domains share the same label-sets.
StruMPL: Multi-task Dense Regression under Disjoint Partial Supervision and MNAR Labels
School of Geosciences, University of Edinburgh, UK（爱丁堡大学地球科学学院，英国）；National Centre for Earth Observation (NCEO), UK（英国地球观测国家中心）；Department of Spatial Sciences, Faculty of Environmental Sciences Czech University of Life Sciences Prague, Praha, Czech Republic（环境科学学院空间科学系，捷克布拉格生命科学大学）
Learning Cross-domain Semantic-Visual Relationships for Transductive Zero-Shot Learning
Southwest Jiaotong University（西南交通大学）；University of Electronic Science and Technology of China（电子科技大学）；Chongqing University（重庆大学）；Guangzhou University（广州大学）
Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering
School of Computer Science and Engineering, Southern University of Science and Technology（南方科技大学计算机科学与工程学院）；College of Big Data and Internet, Shenzhen Technology University（深圳技术大学大数据与互联网学院）
Self-Supervised Federated Learning under Data Heterogeneity for Label-Scarce Diatom Classification
Biodata Mining Group, Faculty of Technology, University of Bielefeld（比勒费尔德大学技术学院生物数据挖掘组）；Computer Science Research Centre, University of Surrey（萨里大学计算机科学研究中心）；Phycology Group, Faculty of Biology, University of Duisburg-Essen（杜伊斯堡-埃森大学生物学院藻类学组）
LetsMap: Unsupervised Representation Learning for Semantic BEV Mapping
University of Freiburg（弗莱堡大学）；Qualcomm SARL France（法国高通公司）；QT Technologies Ireland Limited（爱尔兰QT技术有限公司）；Federal University of Rio Grande（里奥格兰德联邦大学）；University of Technology Nuremberg（纽伦堡工业大学）
