3 Hits in 1.8 sec

SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning [article]

Colorado J Reed, Sean Metzger, Aravind Srinivas, Trevor Darrell, Kurt Keutzer
2021 arXiv   pre-print
We establish this correlation across hundreds of augmentation policies, training settings, and network architectures and provide an algorithm (SelfAugment) to automatically and efficiently select augmentation  ...  Despite not using any labeled data, the learned augmentation policies perform comparably with augmentation policies that were determined using exhaustive supervised evaluations.  ...  We would additionally like to thank Pieter Abbeel, Tete Xiao, Roi Herzig, and Amir Bar for helpful feedback and discussions.  ... 
arXiv:2009.07724v3 fatcat:e4tmeetpvzckdbqlcgccsklr7u

A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classication Tasks [article]

Zihan Yang, Richard O. Sinnott, James Bailey, Qiuhong Ke
2022 arXiv   pre-print
To mitigate such problem, a novel direction is to automatically learn the image augmentation policies from the given dataset using Automated Data Augmentation (AutoDA) techniques.  ...  This paper presents the major works in AutoDA field, discussing their pros and cons, and proposing several potential directions for future improvements.  ...  Self-supervised evaluation is also found useful for detection training [102] .  ... 
arXiv:2206.06544v1 fatcat:wxub4chlbrhbdpzt7g6ydjwu2u

Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning [article]

Ajinkya Tejankar, Soroush Abbasi Koohpayegani, KL Navaneet, Kossar Pourahmadi, Akshayvarun Subramanya, Hamed Pirsiavash
2021 arXiv   pre-print
The prior work on applying mean-shift idea for self-supervised learning, MSF, generalizes the BYOL idea by pulling a query image to not only be closer to its other augmentation, but also to the nearest  ...  We are interested in representation learning in self-supervised, supervised, or semi-supervised settings.  ...  Selfaugment: Automatic 12th International Conference on Computer Vision, pages augmentation policies for self-supervised learning. In 48–55.  ... 
arXiv:2112.04607v1 fatcat:n7g5f2obnzf6xjn6jpyjpp4ezu