High-dimensional deep neural network representations of images and concepts can be aligned to predict human annotations of diverse stimuli. However, such alignment requires the costly collection of behavioral responses, such that, in practice, the deep-feature spaces are only ever sparsely sampled. Here, we propose an active learning approach to adaptively sampling experimental stimuli to efficiently learn a Bayesian matrix factorization model with deep side information. We observe a significant efficiency gain over a passive baseline. Furthermore, with a sequential batched sampling strategy, the algorithm is applicable not only to small datasets collected from traditional laboratory experiments but also to settings where large-scale crowdsourced data collection is needed to accurately align the high-dimensional deep feature representations derived from pre-trained networks.
Multiple Kronecker RLS fusion-based link propagation for drug-side effect prediction
University of Electronic Science and Technology of China(电子科技大学);University of Nottingham Ningbo(宁波诺丁汉大学);Halmstad University(哈尔姆斯塔德大学);Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China(电子科技大学长三角研究院(衢州))
FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion
School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China(计算机学院、多媒体软件国家工程研究中心、多媒体与网络通信工程湖北省重点实验室、武汉大学);Shenzhen Campus of Sun Yat-sen University, China(中山大学深圳校区);Beijing Institute of Technology, Beijing, China(北京理工大学);Nanyang Technological University, Singapore(南洋理工大学)
RMMDet: Road-Side Multitype and Multigroup Sensor Detection System for Autonomous Driving
Shanghai Jiao Tong University(上海交通大学);East China Normal University(华东师范大学);Xin Dong Interactive Entertainment Company Ltd(鑫东互动娱乐有限公司);Summer Son Smart Technology Company Ltd(夏之子智能科技有限公司)
Decentralized Data Fusion and Active Sensing with Mobile Sensors for Modeling and Predicting Spatiotemporal Traffic Phenomena
MIT(麻省理工学院);National University of Singapore(新加坡国立大学);Carnegie Mellon University(卡内基梅隆大学);Singapore-MIT Alliance for Research and Technology(新加坡-麻省理工学院科研联盟);University of Southern California(南加州大学)
E2E Learning Massive MIMO for Multimodal Semantic Non-Orthogonal Transmission and Fusion
School of Information and Electronics, Beijing Institute of Technology (BIT)(信息与电子学院,北京理工大学);State Key Laboratory of Environment Characteristics and Effects for Near-space, Beijing(临近空间环境特征与效应国家重点实验室,北京);State Key Laboratory of CNS/ATM, Beijing(CNS/ATM国家重点实验室,北京);MIIT Key Laboratory of Complex-Field Intelligent Sensing, Beijing(工信部复杂场智能感知重点实验室,北京);BIT, Zhuhai(珠海北京理工大学);Advanced Technology Research Institute, BIT, Jinan(北京理工大学济南先进技术研究院);Yangtze Delta Region Academy, BIT, Jiaxing(长江三角洲地区学院,北京理工大学嘉兴)
Decentralized Data Fusion and Active Sensing with Mobile Sensors for Modeling and Predicting Spatiotemporal Traffic Phenomena
National University of Singapore(新加坡国立大学);Singapore-MIT Alliance for Research and Technology(新加坡-麻省理工学院研究与技术联盟);MIT(麻省理工学院);Carnegie Mellon University(卡内基梅隆大学);University of Southern California(南加州大学)
REL-SF4PASS: Panoramic Semantic Segmentation with REL Depth Representation and Spherical Fusion
School of Electronic and Information Engineering, Shanghai DianJi University(电子信息学院,上海电机大学);College of Computer Science and Technology, Zhejiang University(计算机科学与技术学院,浙江大学)