Just Noticeable Difference Modeling for Deep Visual Features
深度视觉特征的可察觉差异建模
机构 * College of Computing and Data Science, Nanyang Technological University, Singapore(新加坡南洋理工大学计算与数据科学学院) ; Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China(哈尔滨工业大学计算机科学与技术学院) ; School of Artificial Intelligence, Beijing Normal University, Beijing, China(北京师范大学人工智能学院) ; School of Computer Science, Peking University, Beijing, China(北京大学计算机学院)
AI总结 本文提出FeatJND模型,用于深度视觉特征的可察觉差异建模,通过任务对齐的容忍边界提升特征质量控制和量化效率。