2 papers
cs.LG2022
Zeroth-Order Hard-Thresholding: Gradient Error vs. Expansivity
William de Vazelhes, Hualin Zhang, Huimin Wu +2
constrained optimization is prevalent in machine learning, particularly for high-dimensional problems, because it is a fundamental approach to achieve sparse learning. Har…
cs.CV2022
Sample hardness based gradient loss for long-tailed cervical cell detection
Minmin Liu, Xuechen Li, Xiangbo Gao +3
Due to the difficulty of cancer samples collection and annotation, cervical cancer datasets usually exhibit a long-tailed data distribution. When training a detector to detect the…