Distribution Estimation to Automate Transformation Policies for Self-Supervision

11/24/2021
by   Seunghan Yang, et al.
19

In recent visual self-supervision works, an imitated classification objective, called pretext task, is established by assigning labels to transformed or augmented input images. The goal of pretext can be predicting what transformations are applied to the image. However, it is observed that image transformations already present in the dataset might be less effective in learning such self-supervised representations. Building on this observation, we propose a framework based on generative adversarial network to automatically find the transformations which are not present in the input dataset and thus effective for the self-supervised learning. This automated policy allows to estimate the transformation distribution of a dataset and also construct its complementary distribution from which training pairs are sampled for the pretext task. We evaluated our framework using several visual recognition datasets to show the efficacy of our automated transformation policy.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/24/2019

Towards a Hypothesis on Visual Transformation based Self-Supervision

We propose the first qualitative hypothesis characterizing the behavior ...
research
07/27/2022

Optimizing transformations for contrastive learning in a differentiable framework

Current contrastive learning methods use random transformations sampled ...
research
02/18/2020

Data Transformation Insights in Self-supervision with Clustering Tasks

Self-supervision is key to extending use of deep learning for label scar...
research
02/14/2022

A Generic Self-Supervised Framework of Learning Invariant Discriminative Features

Self-supervised learning (SSL) has become a popular method for generatin...
research
03/14/2017

Discriminate-and-Rectify Encoders: Learning from Image Transformation Sets

The complexity of a learning task is increased by transformations in the...
research
08/26/2020

Self-Supervised Human Activity Recognition by Augmenting Generative Adversarial Networks

This article proposes a novel approach for augmenting generative adversa...
research
12/14/2021

On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation

Self-supervised learning is a powerful way to learn useful representatio...

Please sign up or login with your details

Forgot password? Click here to reset