Other / n/a


Kevin McGuinness
Noel E. O'Connor
Eric Arazo


Computer Science

self supervised agglomerative clustering computer vision neural networks learning methods unsupervised learning engineering clustering algorithm

Improving Unsupervised Learning With Exemplar CNNS (2019)

Abstract Most recent unsupervised learning methods explore alternative objectives, often referred to as self-supervised tasks, to train convolutional neural networks without the supervision of human annotated labels. This paper explores the generation of surrogate classes as a self-supervised alternative to learn discriminative features, and proposes a clustering algorithm to overcome one of the main limitations of this kind of approach. Our clustering technique improves the initial implementation and achieves 76.4% accuracy in the STL-10 test set, surpassing the current state-ofthe- art for the STL-10 unsupervised benchmark. We also explore several issues with the unlabeled set from STL-10 that should be considered in future research using this dataset.
Collections Ireland -> TU Dublin -> Session 3: Deep Learning for Computer Vision
Ireland -> TU Dublin -> IMVIP 2019: Irish Machine Vision and Image Processing
Ireland -> TU Dublin -> Colleges
Ireland -> TU Dublin -> College of Engineering and Built Environment
Ireland -> TU Dublin -> Conferences: Engineering and Built Environment

Full list of authors on original publication

Kevin McGuinness, Noel E. O'Connor, Eric Arazo

Experts in our system

Kevin McGuinness
Dublin City University
Total Publications: 93
Noel E. O'Connor
Dublin City University
Total Publications: 474
Eric Arazo
Dublin City University
Total Publications: 4