Improving the performance of inductive learning classifiers through the presentation order of the training patterns

Ruz, Gonzalo A.

doi:10.1016/j.eswa.2016.04.003

Cited by 3 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this algorithm was tested only for classification on benchmark databases without considering experimental data for real-life applications. The performance of the inductive rules family classifiers has been improved by presenting a new technique for the presentation order of the training samples, which combines a clustering method with a density measure function [ 21 ]. The main drawback of this approach is that the convergence to a good result could be quite time-consuming especially when the training set contains thousands of samples.…”

Section: Related Work On Active Semi-supervised Learningmentioning

confidence: 99%

On the Use of Deep Active Semi-Supervised Learning for Fast Rendering in Global Illumination

Constantin

Bigand

2020

J. Imaging

View full text Add to dashboard Cite

Convolution neural networks usually require large labeled data-sets to construct accurate models. However, in many real-world scenarios, such as global illumination, labeling data are a time-consuming and costly human intelligent task. Semi-supervised learning methods leverage this issue by making use of a small labeled data-set and a larger set of unlabeled data. In this paper, our contributions focus on the development of a robust algorithm that combines active and deep semi-supervised convolution neural network to reduce labeling workload and to accelerate convergence in case of real-time global illumination. While the theoretical concepts of photo-realistic rendering are well understood, the increased need for the delivery of highly dynamic interactive content in vast virtual environments has increased recently. Particularly, the quality measure of computer-generated images is of great importance. The experiments are conducted on global illumination scenes which contain diverse distortions. Compared with human psycho-visual thresholds, the good consistency between these thresholds and the learning models quality measures can been seen. A comparison has also been made with SVM and other state-of-the-art deep learning models. We do transfer learning by running the convolution base of these models over our image set. Then, we use the output features of the convolution base as input to retrain the parameters of the fully connected layer. The obtained results show that our proposed method provides promising efficiency in terms of precision, time complexity, and optimal architecture.

show abstract

Section: Related Work On Active Semi-supervised Learningmentioning

confidence: 99%