IIIT-Delhi Institutional Repository

Semi-supervised learning via triplet network based active learning

Show simple item record

dc.contributor.author Sundriyal, Divyanshu
dc.contributor.author Vatsa, Mayank (Advisor)
dc.contributor.author Singh, Richa (Advisor)
dc.date.accessioned 2021-03-24T09:45:08Z
dc.date.available 2021-03-24T09:45:08Z
dc.date.issued 2020-06
dc.identifier.uri http://repository.iiitd.edu.in/xmlui/handle/123456789/856
dc.description.abstract Deep learning systems require a large amount of labelled training dataset. However large amount of labelled data is not available in many cases as it requires considerable human effort to label each sample correctly. In many cases like medical imaging, there is a small amount of labelled dataset along with large amount of unlabelled samples. In this research, we implement an Active learning algorithm which can help in increasing performance of deep learning models by using large amount of available unlabelled dataset. We propose a novel Active learning algorithm (Triplet AL) which uses a triplet network to select samples from unlabelled set for training classification model. Past active learning methods rely on classification model's final prediction scores as a measure of confidence for an unlabelled sample. We propose a more reliable confidence measure called Top-Two-Margin which is given by Triplet Network. We used STL-10 and CIFAR-10 dataset to test proposed algorithm. To test architectural independence of proposed algorithm, we tested proposed algorithm by using different model architectures for classification model. We compared results obtained using proposed method with past active learning methods. Proposed algorithm outperforms other active learning approaches we used to compare in our research. en_US
dc.language.iso en_US en_US
dc.publisher IIIT-Delhi en_US
dc.subject Active Learning, CNN, Triplet loss, Semi-Supervised learning en_US
dc.title Semi-supervised learning via triplet network based active learning en_US
dc.type Thesis en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search Repository

Advanced Search


My Account