Band selection has a great impact on the spectral recovery quality. To solve this ill-posed inverse problem, most band selection methods adopt hand-crafted priors or exploit clustering or sparse regularization constraints to find most prominent bands. These methods are either very slow due to the computational cost of repeatedly training with respect to different selection frequencies or different band combinations. Many traditional methods rely on the scene prior and thus are not applicable to other scenarios. In this paper, we present a novel one-shot Neural Band Selection (NBS) framework for spectral recovery. Unlike conventional searching approaches with a discrete search space and a non-differentiable search strategy, our NBS is based on the continuous relaxation of the band selection process, thus allowing efficient band search using gradient descent. To enable the compatibility for se- lecting any number of bands in one-shot, we further exploit the band-wise correlation matrices to progressively suppress similar adjacent bands. Extensive evaluations on the NTIRE 2022 Spectral Reconstruction Challenge demonstrate that our NBS achieves consistent performance gains over competitive baselines when examined with four different spectral recov- ery methods. Our code will be publicly available.
AERR-Nav: Adaptive Exploration-Recovery-Reminiscing Strategy for Zero-Shot Object Navigation
Hong Kong Polytechnic University(香港理工大学);Institute of automation, Chinese Academy of Sciences(中国科学院自动化研究所);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Active few-shot segmentation by reinforcing data selection
Centre for Bioengineering, School of Engineering and Materials Science, Queen Mary University of London(伦敦玛丽女王大学工程与材料科学学院生物工程中心);Digital Environment Research Institute, Queen Mary University of London(伦敦玛丽女王大学数字环境研究所);UCL Hawkes Institute(伦敦大学学院UCL霍克斯研究所;医学物理与生物医学工程系);Department of Medical Physics and Biomedical Engineering, University College London(耶鲁大学生物与生物医学科学系);Department of Biological and Biomedical Sciences, Yale University(牛津大学工程科学系生物医学工程研究所);Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford
MHE-Former: Multi-Hypothesis Transformers via Entropy Maximization for 3D Mesh Recovery
Communication University of China(中国传媒大学);Nankai University(南开大学);Beihang University(北京航空航天大学);East China Normal University(华东师范大学);National University of Singapore(新加坡国立大学)
Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid
Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));University of Electronic Science and Technology of China(电子科技大学);Pengcheng Laboratory(鹏城实验室);Zhejiang Lab(之江实验室)
TALDS-Net: Task-Aware Adaptive Local Descriptors Selection for Few-shot Image Classification
School of Computer Science and Technology, Soochow University(苏州大学计算机科学与技术学院);School of Computer Science(计算机学院);Technology, Soochow University(苏州大学技术学院)
Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset Selection
National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, School of Computer Science, Wuhan University, China(国家多媒体软件工程研究中心、人工智能研究院、计算机科学学院、武汉大学,中国);Hubei Key Laboratory of Multimedia(湖北省多媒体关键实验室);The University of Tokyo, Japan(东京大学,日本);National Institute of Informatics, Japan(日本信息处理学会);School of Computer Science(计算机科学学院);Technology, Wuhan University of Science(科技,武汉科技大学)
LaVida Drive: Vision-Text Interaction VLM for Autonomous Driving with Token Selection, Recovery and Enhancement
National University of Singapore(新加坡国立大学);Tsinghua University(清华大学);Agency for Science, Technology and Research, Singapore(新加坡科技研究局);Advanced Institute of Big Data, Beijing(北京大数据研究院)