Transductive Semi-Supervised Deep Learning using Min-Max Features
In this paper, we propose Transductive Semi-Supervised Deep Learning (TSSDL) method that is effective for training Deep Convolutional Neural Network (DCNN) models. The method applies transductive learning principle to DCNN training, introduces confidence levels on unlabeled image samples to overcome unreliable label estimates on outliers and uncertain samples, and develops the Min-Max Feature (MMF) regularization that encourages DCNN to learn feature descriptors with better between-class separability and within-class compactness. TSSDL method is independent of any DCNN architectures and complementary to the latest Semi-Supervised Learning (SSL) methods. Comprehensive experiments on the benchmark datasets CIFAR10 and SVHN have shown that the DCNN model trained by the proposed TSSDL method can produce image classification accuracies compatible to the state-of-the-art SSL methods, and that combining TSSDL with the Mean Teacher method can produce the best classification accuracies on the two benchmark datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningGeneral Classificationimage-classificationImage ClassificationTransductive LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Transductive Inference and Semi-Supervised Learning
This chapter contains sections titled: Problem Settings, Problem of Generalization in Inductive and Transductive Inference, Structure of the VC Bounds and Transductive Inference, The Symmetrization Lemma and Transductive…
LEMMADeep Transductive Semi-supervised Maximum Margin Clustering
Semi-supervised clustering is an very important topic in machine learning and computer vision. The key challenge of this problem is how to learn a metric, such that the instances sharing the same label are more likely cl…
ClusteringTransductive LearningOptimally Combining Classifiers for Semi-Supervised Learning
This paper considers semi-supervised learning for tabular data. It is widely known that Xgboost based on tree model works well on the heterogeneous features while transductive support vector machine can exploit the low d…
DiversityMachine Translation Model based on Non-parallel Corpus and Semi-supervised Transductive Learning
Although the parallel corpus has an irreplaceable role in machine translation, its scale and coverage is still beyond the actual needs. Non-parallel corpus resources on the web have an inestimable potential value in mach…
Machine TranslationTransductive LearningTranslationEASE: Unsupervised Discriminant Subspace Learning for Transductive Few-Shot Learning
Few-shot learning (FSL) has received a lot of attention due to its remarkable ability to adapt to novel classes. Although many techniques have been proposed for FSL, they mostly focus on improving FSL backbones. Some…
Few-Shot Learning