Add to ORKGMost 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 dat...
© 2018 Association for Computing Machinery. The superiority of deeply learned pedestrian representat...
Unsupervised learning has important applications in extremely large data settings such as in medical...
While supervised learning techniques have become increasinglyadept at separating images into differe...
Most recent unsupervised learning methods explore alternative objectives, often referred to as self-...
Convolutional neural networks (CNNs) have achieved unprecedented success in a variety of computer vi...
Self-supervised learning deals with problems that have little or no available labeled data. Recent w...
Thesis (Ph.D.)--University of Washington, 2020Unsupervised learning is the branch of machine learnin...
This thesis is an investigation of unsupervised learning for image classification. The state-of-the-...
We present a novel clustering objective that learns a neural network classifier from scratch, given ...
This master thesis tackles the problem of unsupervised learning of visual representations with deep ...
International audiencePre-training general-purpose visual features with convolutional neural network...
Abstract—Deep convolutional networks have proven to be very successful in learning task specific fea...
In this paper, we propose a new clustering module that can be trained jointly with existing neural n...
Ntelemis F, Jin Y, Thomas SA. Information maximization clustering via multi-view self-labelling. Kno...
Current methods for training convolutional neural networks depend on large amounts of labeled sample...
© 2018 Association for Computing Machinery. The superiority of deeply learned pedestrian representat...
Unsupervised learning has important applications in extremely large data settings such as in medical...
While supervised learning techniques have become increasinglyadept at separating images into differe...
Most recent unsupervised learning methods explore alternative objectives, often referred to as self-...
Convolutional neural networks (CNNs) have achieved unprecedented success in a variety of computer vi...
Self-supervised learning deals with problems that have little or no available labeled data. Recent w...
Thesis (Ph.D.)--University of Washington, 2020Unsupervised learning is the branch of machine learnin...
This thesis is an investigation of unsupervised learning for image classification. The state-of-the-...
We present a novel clustering objective that learns a neural network classifier from scratch, given ...
This master thesis tackles the problem of unsupervised learning of visual representations with deep ...
International audiencePre-training general-purpose visual features with convolutional neural network...
Abstract—Deep convolutional networks have proven to be very successful in learning task specific fea...
In this paper, we propose a new clustering module that can be trained jointly with existing neural n...
Ntelemis F, Jin Y, Thomas SA. Information maximization clustering via multi-view self-labelling. Kno...
Current methods for training convolutional neural networks depend on large amounts of labeled sample...
© 2018 Association for Computing Machinery. The superiority of deeply learned pedestrian representat...
Unsupervised learning has important applications in extremely large data settings such as in medical...
While supervised learning techniques have become increasinglyadept at separating images into differe...