Contrastive Model: Instance-Instance

#Self-supervised Learning #Contrastive Model #Basics

It was discovered that the success of [[mutual information based contrastive learning]] Contrastive Model: Context-Instance In contrastive methods, we can manipulate the data to create data entries and infer the changes using a model. These methods are models that “predict relative position”1. Common tricks are shuffling image sections like jigsaw, and rotate the image. We can also adjust the model to discriminate the similarities and differences. For example, to generate contrast, we can also use [[Mutual Information]] Mutual Information Mutual information is defined as $$ I(X;Y) = \mathbb E_{p_{XY}} \ln … is more related to the encoder architecture and the negative sampling strategy¹. Instance-instance method is more direct in solving the contrastive problem. It take the instance itself directly and make comparisons for discrimination.

Cluster Discrimination

Illustration of Deep Cluster based on Liu2020.

Instance Discrimination

There are two interesting models under the umbrella of instance discrimination,

MoCo, and
SimCLR.

Illustration of MoCo based on Liu2020.

Illustration of SimCLR based on Liu2020.

Liu2020 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 ↩︎

Planted: 2021-08-13 by L Ma;

References:

Liu2020 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:

Contrastive Model

Contrastive models learn to compare1. Contrastive use special objective functions such as [[NCE]] …

Contrastive Model: Context-Instance

In contrastive methods, we can manipulate the data to create data entries and infer the changes …

An Introduction to Generative Models

Discriminative model: The conditional probability of class label on data (posterior) $p(C_k\mid x)$ …

The task of GAN is to generate features $X$ from some noise $\xi$ and class labels $Y$, $$\xi, Y \to …

Additional Double Backet Links:

Contrastive Model: Context-Instance

In contrastive methods, we can manipulate the data to create data entries and infer the changes …

L Ma (2021). 'Contrastive Model: Instance-Instance', Datumorphism, 08 April. Available at: https://datumorphism.leima.is/wiki/machine-learning/contrastive-models/instance-instance/.