Search results
Jan 21, 2021 · We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and self-supervised learning of deep neural networks.
- Lang Huang, Chao Zhang, Hongyang Zhang
- arXiv:2101.08732 [cs.LG]
- 2021
Nov 15, 2019 · Semi-supervised learning is a branch of machine learning that aims to combine these two tasks (Chapelle et al. 2006b; Zhu 2008 ). Typically, semi-supervised learning algorithms attempt to improve performance in one of these two tasks by utilizing information generally associated with the other.
- Jesper E. van Engelen, Holger H. Hoos, Holger H. Hoos
- 2020
Domain adaptation (DA) aims to transfer representations of source categories to novel target domains without additional supervision. Recent deep DA methods primarily achieve this by minimizing the feature distribution shift between the source and target samples [11, 24, 38].
- 835KB
- Kuniaki Saito, Donghyun Kim, Stan Sclaroff, Kate Saenko
- 11
- 2020
Jan 1, 2018 · This paper introduces an innovative approach for supervised learning systems in cases when we do not have initially defined training data sets, but we need to develop them gradually during ...
Aug 11, 2022 · In this Review, we highlight self-supervised methods and models for use in medicine and healthcare, and discuss the advantages and limitations of their application to tasks involving electronic...
Jun 10, 2021 · Domain adaptation to ED3, ED2 and ED1 using MD-nets was achieved in an unsupervised manner. The networks were initially tested with a hold-out test set of 742 ED4 embryo images, followed by tests...
Jul 1, 2016 · This paper is a brief review of adaptation mechanisms in unsupervised learning focusing on approaches recently reported in the literature for adaptive clustering and novelty detection and discussing some future directions.
