120 citations · 183 across the 8 of their papers we have counts for
8 papers
Multi-view Feature Augmentation with Adaptive Class Activation Mapping
Xiang Gao, Yingjie Tian, Zhiquan Qi
We propose an end-to-end-trainable feature augmentation module built for image classification that extracts and exploits multi-view local features to boost model performance. Diffe…
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…
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…
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…
Joint Ranking SVM and Binary Relevance with Robust Low-Rank Learning for Multi-Label Classification
Guoqiang Wu, Ruobing Zheng, Yingjie Tian +1
Multi-label classification studies the task where each example belongs to multiple labels simultaneously. As a representative method, Ranking Support Vector Machine (Rank-SVM) aims…
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…
PIGMIL: Positive Instance Detection via Graph Updating for Multiple Instance Learning
Dongkuan Xu, Jia Wu, Wei Zhang +1
Positive instance detection, especially for these in positive bags (true positive instances, TPIs), plays a key role for multiple instance learning (MIL) arising from a specific cl…
Multi-view metric learning for multi-instance image classification
Dewei Li, Yingjie Tian
It is critical and meaningful to make image classification since it can help human in image retrieval and recognition, object detection, etc. In this paper, three-sides efforts are…