17 citations · 69 across the 11 of their papers we have counts for
4 papers · 1 filter
Temporal Output Discrepancy for Loss Estimation-based Active Learning
Siyu Huang, Tianyang Wang, Haoyi Xiong +3
While deep learning succeeds in a wide range of tasks, it highly depends on the massive collection of annotated data which is expensive and time-consuming. To lower the cost of dat…
Deep Active Learning with Noise Stability
Xingjian Li, Pengkun Yang, Yangcheng Gu +4
Uncertainty estimation for unlabeled data is crucial to active learning. With a deep neural network employed as the backbone model, the data selection process is highly challenging…
Towards Inadequately Pre-trained Models in Transfer Learning
Andong Deng, Xingjian Li, Di Hu +3
Pre-training has been a popular learning paradigm in deep learning era, especially in annotation-insufficient scenario. Better ImageNet pre-trained models have been demonstrated, f…
Boosting Active Learning via Improving Test Performance
Tianyang Wang, Xingjian Li, Pengkun Yang +5
Central to active learning (AL) is what data should be selected for annotation. Existing works attempt to select highly uncertain or informative data for annotation. Nevertheless,…