K Wang, D Zhang, Y Li, R Zhang… - IEEE Transactions on …, 2016 - ieeexplore.ieee.org
… In this paper, we propose a novel activelearning framework, which is capable of building a … incremental learning manner. Our approach advances the existing activelearning methods …
… We compare the performance of acquisition functions and uncertainty estimation methods for activelearning with CNNs on imageclassification tasks. We show that ensemble-based …
D Tuia, M Volpi, L Copa, M Kanevski… - IEEE Journal of …, 2011 - ieeexplore.ieee.org
… This paper reviews and tests the main families of activelearning algorithms: committee, … imageclassification tasks. This paper presents the general framework of activelearning and …
X Li, Y Guo - Proceedings of the IEEE conference on …, 2013 - openaccess.thecvf.com
… an activelearning strategy. In this paper, we propose a novel adaptive activelearning … In this paper, we develop a new activelearning method for image classification tasks, which …
D Tuia, F Ratle, F Pacifici, MF Kanevski… - IEEE Transactions on …, 2009 - ieeexplore.ieee.org
… In this paper, we have presented an activelearning framework for remote sensing image classification. In this framework, the predictor has control on the composition of the training set …
X Li, L Wang, E Sung - 2004 International Conference on Image …, 2004 - ieeexplore.ieee.org
… N ow the multi-label SVM is introduced, which will be used for activelearning in this paper. Multi-label SVM uses the one-versus4 method to combine predictions of multiple hinary SVM …
… a novel activelearning … activelearning task and train the model to minimize the loss function. To the best of our knowledge, this is the first research effort to integrate an activelearning …
… imageclassification community. In this work, a more comprehensive survey focusing on multi-label activelearning for imageclassification is … components of an activelearning system. …
X Cao, J Yao, Z Xu, D Meng - IEEE Transactions on Geoscience …, 2020 - ieeexplore.ieee.org
… In order to improve the classification performance while reducing the … an active deep learning approach for HSI classification, which integrates both activelearning and deep learning …