activity
20192021
most citedFast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function

52 citations · 73 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CV202115 cited

Visual Anomaly Detection for Images: A Survey

Jie Yang, Ruijie Xu, Zhiquan Qi +1

Visual anomaly detection is an important and challenging problem in the field of machine learning and computer vision. This problem has attracted a considerable amount of attention…

cs.CV202152 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…

eess.IV20202 cited

Concatenated Attention Neural Network for Image Restoration

Tian YingJie, Wang YiQi, Yang LinRui +1

In this paper, we present a general framework for low-level vision tasks including image compression artifacts reduction and image denoising. Under this framework, a novel concaten…

cs.CV20204 cited

Learning to Incorporate Structure Knowledge for Image Inpainting

Jie Yang, Zhiquan Qi, Yong Shi

This paper develops a multi-task learning framework that attempts to incorporate the image structure knowledge to assist image inpainting, which is not well explored in previous wo…

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…