output
19982026
most citedRecent Advances in Open Set Recognition: A Survey

1k citations

Showing 2018 · cs.LGShow all

8 papers · 2 filters

cs.LG2018★ 1k cited

Recent Advances in Open Set Recognition: A Survey

Chuanxing Geng, Sheng-jun Huang, Songcan Chen

In real-world recognition/classification tasks, limited by various objective factors, it is usually difficult to collect training samples to exhaust all classes when training a rec…

cs.LG2018★ 8 cited

Graph Convolutional Neural Networks via Motif-based Attention

Hao Peng, Jianxin Li, Qiran Gong +3

Many real-world problems can be represented as graph-based learning problems. In this paper, we propose a novel framework for learning spatial and attentional convolution neural ne…

cs.LG2018★ 36 cited

Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories

Huanhuan Yu, Menglei Hu, Songcan Chen

Unsupervised domain adaptation (UDA) aims to learn the unlabeled target domain by transferring the knowledge of the labeled source domain. To date, most of the existing works focus…

cs.LG2018★ 1 cited

Gradient Hyperalignment for multi-subject fMRI data alignment

Tonglin Xu, Muhammad Yousefnezhad, Daoqiang Zhang

Multi-subject fMRI data analysis is an interesting and challenging problem in human brain decoding studies. The inherent anatomical and functional variability across subjects make…

cs.LG2018★ 49 cited

Collective decision for open set recognition

Chuanxing Geng, Songcan Chen

In open set recognition (OSR), almost all existing methods are designed specially for recognizing individual instances, even these instances are collectively coming in batch. Recog…

cs.LG2018★ 1 cited

Brain EEG Time Series Selection: A Novel Graph-Based Approach for Classification

Chenglong Dai, Jia Wu, Dechang Pi +1

Brain Electroencephalography (EEG) classification is widely applied to analyze cerebral diseases in recent years. Unfortunately, invalid/noisy EEGs degrade the diagnosis performanc…

cs.LG2018★ 3 cited

Cost-Effective Training of Deep CNNs with Active Model Adaptation

Sheng-Jun Huang, Jia-Wei Zhao, Zhao-Yang Liu

Deep convolutional neural networks have achieved great success in various applications. However, training an effective DNN model for a specific task is rather challenging because i…

cs.LG2018★ 8 cited

Active Feature Acquisition with Supervised Matrix Completion

Sheng-Jun Huang, Miao Xu, Ming-Kun Xie +3

Feature missing is a serious problem in many applications, which may lead to low quality of training data and further significantly degrade the learning performance. While feature…