computer-vision-11
Self-Supervised Learning
3260 papers • 126 benchmarks • 313 datasets
Self-Supervised Learning is proposed for utilizing unlabeled data with the success of supervised learning. Producing a dataset with good labels is expensive, while unlabeled data is being generated all the time. The motivation of Self-Supervised Learning is to make use of the large amount of unlabeled data. The main idea of Self-Supervised Learning is to generate the labels from unlabeled data, according to the structure or characteristics of the data itself, and then train on this unsupervised data in a supervised manner. Self-Supervised Learning is wildly used in representation learning to make a model learn the latent features of the data. This technique is often employed in computer vision, video processing and robot control. Source: Self-supervised Point Set Local Descriptors for Point Cloud Registration Image source: LeCun
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in self-supervised-learning-11
Trend
Dataset
Best Model
Actions
STL-10
STL-10
DABS
DABS
Libraries
iUse these libraries to find self-supervised-learning-11 models and implementations
14 papers 2,843
Datasets
Subtasks
Most implemented papers
A Simple Framework for Contrastive Learning of Visual Representations
Geoffrey E. Hinton, Mohammad Norouzi, Ting Chen, Simon Kornblith•Wed Feb 12 2020
It is shown that composition of data augmentations plays a critical role in defining effective predictive tasks, and introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning.
