Evolutionary Augmentation Policy Optimization for Self-supervised Learning

2023-03-02 · Noah Barrett, Zahra Sadeghi, Stan Matwin

Self-supervised Learning (SSL) is a machine learning algorithm for pretraining Deep Neural Networks (DNNs) without requiring manually labeled data. The central idea of this learning technique is based on an auxiliary stage aka pretext task in which labeled data are created automatically through data augmentation and exploited for pretraining the DNN. However, the effect of each pretext task is not well studied or compared in the literature. In this paper, we study the contribution of augmentation operators on the performance of self supervised learning algorithms in a constrained settings. We propose an evolutionary search method for optimization of data augmentation pipeline in pretext tasks and measure the impact of augmentation operators in several SOTA SSL algorithms. By encoding different combination of augmentation operators in chromosomes we seek the optimal augmentation policies through an evolutionary optimization mechanism. We further introduce methods for analyzing and explaining the performance of optimized SSL algorithms. Our results indicate that our proposed method can find solutions that outperform the accuracy of classification of SSL algorithms which confirms the influence of augmentation policy choice on the overall performance of SSL algorithms. We also compare optimal SSL solutions found by our evolutionary search mechanism and show the effect of batch size in the pretext task on two visual datasets.

📄 PDF Abstract BibTeX arXiv:2303.01584

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation Self-Supervised Learning

Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?

2022-06-10 · Xiang Li, Jinghuan Shang, Srijan Das, Michael S. Ryoo

We investigate whether self-supervised learning (SSL) can improve online reinforcement learning (RL) from pixels. We extend the contrastive reinforcement learning framework (e.g., CURL) that jointly optimizes SSL and RL …

Image Augmentation reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimization

2026-03-13 · Ruicheng Zhang, Guangyu Chen, Zunnan Xu, Zihao Liu 외 arxiv

Scalable Embodied AI faces fundamental constraints due to prohibitive costs and safety risks of real-world interaction. While Embodied World Models (EWMs) offer promise through imagined rollouts, existing approaches suff…

ViewMix: Augmentation for Robust Representation in Self-Supervised Learning

2023-09-06 · Arjon Das, Xin Zhong

Joint Embedding Architecture-based self-supervised learning methods have attributed the composition of data augmentations as a crucial factor for their strong representation learning capabilities. While regional dropout …

Representation Learning Self-Supervised Learning

SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies

2021-06-17 · Linxi Fan, Guanzhi Wang, De-An Huang, Zhiding Yu 외

Generalization has been a long-standing challenge for reinforcement learning (RL). Visual RL, in particular, can be easily distracted by irrelevant factors in high-dimensional observation space. In this work, we consider…

Autonomous Driving Image Augmentation Reinforcement Learning (RL)Representation Learning+1

SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning

2020-09-16 · CVPR 2021 1 · Colorado J Reed, Sean Metzger, Aravind Srinivas, Trevor Darrell 외

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 p…

Data Augmentation Representation Learning Self-Supervised Learning