Related papers: SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning

SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning

URL: http://arxiv.org/abs/2009.07724v3
Date: Mon, 17 May 2021 15:11:06 GMT
Title: SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning
Authors: Colorado J Reed, Sean Metzger, Aravind Srinivas, Trevor Darrell, Kurt Keutzer
Abstract summary: We show that evaluating the learned representations with a self-supervised image rotation task is highly correlated with a standard set of supervised evaluations. We provide an algorithm (SelfAugment) to automatically and efficiently select augmentation policies without using supervised evaluations.
Score: 98.2036247050674
License: http://creativecommons.org/publicdomain/zero/1.0/
Abstract: A common practice in unsupervised representation learning is to use labeled data to evaluate the quality of the learned representations. This supervised evaluation is then used to guide critical aspects of the training process such as selecting the data augmentation policy. However, guiding an unsupervised training process through supervised evaluations is not possible for real-world data that does not actually contain labels (which may be the case, for example, in privacy sensitive fields such as medical imaging). Therefore, in this work we show that evaluating the learned representations with a self-supervised image rotation task is highly correlated with a standard set of supervised evaluations (rank correlation $> 0.94$). 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 policies without using supervised evaluations. Despite not using any labeled data, the learned augmentation policies perform comparably with augmentation policies that were determined using exhaustive supervised evaluations.

Related papers

A review on discriminative self-supervised learning methods [6.24302896438145]
Self-supervised learning has emerged as a method to extract robust features from unlabeled data. This paper provides a review of discriminative approaches of self-supervised learning within the domain of computer vision.
arXiv Detail & Related papers (2024-05-08T11:15:20Z)
Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
arXiv Detail & Related papers (2023-06-23T17:59:09Z)
Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach [95.74102207187545]
We show that a prior-free autonomous data augmentation's objective can be derived from a representation learning principle. We then propose a practical surrogate to the objective that can be efficiently optimized and integrated seamlessly into existing methods.
arXiv Detail & Related papers (2022-11-02T02:02:51Z)
Simple Control Baselines for Evaluating Transfer Learning [1.0499611180329802]
We share an evaluation standard that aims to quantify and communicate transfer learning performance. We provide an example empirical study investigating a few basic questions about self-supervised learning.
arXiv Detail & Related papers (2022-02-07T17:26:26Z)
Curriculum Offline Imitation Learning [72.1015201041391]
offline reinforcement learning tasks require the agent to learn from a pre-collected dataset with no further interactions with the environment. We propose textitCurriculum Offline Learning (COIL), which utilizes an experience picking strategy for imitating from adaptive neighboring policies with a higher return. On continuous control benchmarks, we compare COIL against both imitation-based and RL-based methods, showing that it not only avoids just learning a mediocre behavior on mixed datasets but is also even competitive with state-of-the-art offline RL methods.
arXiv Detail & Related papers (2021-11-03T08:02:48Z)
Offline Reinforcement Learning with Implicit Q-Learning [85.62618088890787]
Current offline reinforcement learning methods need to query the value of unseen actions during training to improve the policy. We propose an offline RL method that never needs to evaluate actions outside of the dataset. This method enables the learned policy to improve substantially over the best behavior in the data through generalization.
arXiv Detail & Related papers (2021-10-12T17:05:05Z)
In Automation We Trust: Investigating the Role of Uncertainty in Active Learning Systems [5.459797813771497]
We investigate how different active learning (AL) query policies coupled with classification uncertainty visualizations affect analyst trust in automated classification systems. We find that query policy significantly influences an analyst's trust in an image classification system. We propose a set of oracle query policies and visualizations for use during AL training phases that can influence analyst trust in classification.
arXiv Detail & Related papers (2020-04-02T00:52:49Z)
How Useful is Self-Supervised Pretraining for Visual Tasks? [133.1984299177874]
We evaluate various self-supervised algorithms across a comprehensive array of synthetic datasets and downstream tasks. Our experiments offer insights into how the utility of self-supervision changes as the number of available labels grows.
arXiv Detail & Related papers (2020-03-31T16:03:22Z)
Reinforcement learning for the privacy preservation and manipulation of eye tracking data [12.486057928762898]
We present an approach based on reinforcement learning for eye tracking data manipulation. We show that our approach is successfully applicable to preserve the privacy of the subjects.
arXiv Detail & Related papers (2020-02-17T07:02:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.