A generative adversarial network based image transformation policy for visual self-supervision

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and more.Subscribe

CC BY

Source arXiv

Computer Vision

A generative adversarial network based image transformation policy for visual self-supervision

Distribution Estimation to Automate Transformation Policies for Self-Supervision

In recent visual self-supervision works, an imitated classificationobjective, 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.

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 recognitiondatasets to show the efficacy of our automated transformation policy.

Authors

Seunghan Yang, Debasmit Das, Simyung Chang, Sungrack Yun, Fatih Porikli

◐ Recommended Follows

◐ Latest Activity