52 citations · 52 across the 2 of their papers we have counts for
3 papers
cs.CV2021★ 52 cited
Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function
Kai Li, Bo Wang, Yingjie Tian +1
Numerous detection problems in computer vision, including road crack detection, suffer from exceedingly foreground-background imbalance. Fortunately, modification of loss function…
cs.LG2021
Two-stage Training for Learning from Label Proportions
Jiabin Liu, Bo Wang, Xin Shen +2
Learning from label proportions (LLP) aims at learning an instance-level classifier with label proportions in grouped training data. Existing deep learning based LLP methods utiliz…
cs.LG2019
Learning from Label Proportions with Generative Adversarial Networks
Jiabin Liu, Bo Wang, Zhiquan Qi +2
In this paper, we leverage generative adversarial networks (GANs) to derive an effective algorithm LLP-GAN for learning from label proportions (LLP), where only the bag-level propo…