Limberg C, Krieger K, Wersing H, Ritter H. Active Learning for Image Recognition Using a Visualization-Based User Interface. In: Tetko IV, Kůrková V, Karpov P, Theis F, eds. Artificial Neural Networks and Machine Learning – ICANN 2019: Deep Learning. Lecture Notes in Computer Science. Vol 11728. Cham: Springer; 2019: 495-506
The key idea behind active learning is that a machine learning algorithm can achieve greater accurac...
University of Minnesota Ph.D. dissertation. June 2011. Major: Computer Science. Advisor: Nikolaos P....
Currently, image databases have been growing, resulting in the need for optimization and acceleratio...
Active learning has been proven a reliable strategy to reduce manual efforts in training data labeli...
Active learning is a label-efficient machine learning method that actively selects the most valuable...
Classification is a common task in data mining and knowledge discovery. Usually classifiers have to ...
textVisual recognition research develops algorithms and representations to autonomously recognize vi...
Despite the availability and ease of collecting a large amount of free, unlabeled data, the expensiv...
The labeling of data sets is a time-consuming task, which is, however, an important prerequisite for...
Recent advances in visual analytics have enabled us to learn from user interactions and uncover anal...
With active learning, domain expert doesn't need to annotate the whole dataset, but only those which...
Active learning promises to improve annotation efficiency by iteratively selecting the most importan...
<p>Most classic machine learning methods depend on the assumption that humans can annotate all the d...
Active learning aims to label the most informative data points in order to minimize the cost of lab...
Nowadays, the inexpensive memory space promotes an accelerating growth of stored image data. To expl...
The key idea behind active learning is that a machine learning algorithm can achieve greater accurac...
University of Minnesota Ph.D. dissertation. June 2011. Major: Computer Science. Advisor: Nikolaos P....
Currently, image databases have been growing, resulting in the need for optimization and acceleratio...
Active learning has been proven a reliable strategy to reduce manual efforts in training data labeli...
Active learning is a label-efficient machine learning method that actively selects the most valuable...
Classification is a common task in data mining and knowledge discovery. Usually classifiers have to ...
textVisual recognition research develops algorithms and representations to autonomously recognize vi...
Despite the availability and ease of collecting a large amount of free, unlabeled data, the expensiv...
The labeling of data sets is a time-consuming task, which is, however, an important prerequisite for...
Recent advances in visual analytics have enabled us to learn from user interactions and uncover anal...
With active learning, domain expert doesn't need to annotate the whole dataset, but only those which...
Active learning promises to improve annotation efficiency by iteratively selecting the most importan...
<p>Most classic machine learning methods depend on the assumption that humans can annotate all the d...
Active learning aims to label the most informative data points in order to minimize the cost of lab...
Nowadays, the inexpensive memory space promotes an accelerating growth of stored image data. To expl...
The key idea behind active learning is that a machine learning algorithm can achieve greater accurac...
University of Minnesota Ph.D. dissertation. June 2011. Major: Computer Science. Advisor: Nikolaos P....
Currently, image databases have been growing, resulting in the need for optimization and acceleratio...