Self-supervised Learning: Generative or Constrastive

GROWING This note is being developed. It is readible but changes are being applied.
reading/self-supervised-learning-generative-or-contrastive-2006.08218.md Current Note ID: The unique ID of this note.
#machine learning #self-supervised learning

Review of self-supervised learning.

Planted: by ;

References:
  1. Liu X, Zhang F, Hou Z, Wang Z, Mian L, Zhang J, et al. Self-supervised Learning: Generative or Contrastive. arXiv [cs.LG]. 2020. Available: http://arxiv.org/abs/2006.08218
Similar Articles:
Hierarchical Classification
Hierarchical Classification Problem Hierarchical classification labels involves hierarchical class …
Classifier Chains for Multilabel Classification
Classifier chains is a method to predict hierarchical class labels
Normalizing Flows: An Introduction and Review of Current Methods
To generate complicated distributions step by step from a simple and interpretable distribution.
Improving Document Ranking with Dual Word Embeddings
Word2vec produces two embedding spaces, the in-embedding and out-embedding.
reading/self-supervised-learning-generative-or-contrastive-2006.08218 Links to:
Generative Models
Generative self-supervised learning models can utilize more data
Contrastive Models
Contrastive self-supervised learning models can utilize more data
Adversarial Models
Adversarial models use a generator and discriminator

L Ma (2021). 'Self-supervised Learning: Generative or Constrastive', Datumorphism, 08 April. Available at: https://datumorphism.leima.is/reading/self-supervised-learning-generative-or-contrastive-2006.08218/.