Results 11 to 20 of about 97,243 (265)
To Compress or Not to Compress—Self-Supervised Learning and Information Theory: A Review
EntropyDeep neural networks excel in supervised learning tasks but are constrained by the need for extensive labeled data. Self-supervised learning emerges as a promising alternative, allowing models to learn without explicit labels.
Ravid Shwartz Ziv, Yann LeCun
doaj +3 more sources
CONTRASTIVE SELF-SUPERVISED DATA FUSION FOR SATELLITE IMAGERY [PDF]
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2022 Self-supervised learning has great potential for the remote sensing domain, where unlabelled observations are abundant, but labels are hard to obtain. This work leverages unlabelled multi-modal remote sensing data for augmentation-free contrastive self ...
L. Scheibenreif, M. Mommert, D. Borth
doaj +1 more source
EVALUATION OF SELF-SUPERVISED LEARNING APPROACHES FOR SEMANTIC SEGMENTATION OF INDUSTRIAL BURNER FLAMES [PDF]
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2022 In recent years, self-supervised learning has made tremendous progress in closing the gap to supervised learning due to the rapid development of more sophisticated approaches like SimCLR, MoCo, and SwAV.
S. Landgraf +6 more
doaj +1 more source
Self supervised contrastive learning for digital histopathology
Machine Learning with Applications, 2022 Unsupervised learning has been a long-standing goal of machine learning and is especially important for medical image analysis, where the learning can compensate for the scarcity of labeled datasets.
Ozan Ciga, Tony Xu, Anne Louise Martel
doaj +1 more source
Quantum self-supervised learning
Quantum Science and Technology, 2022 AbstractThe resurgence of self-supervised learning, whereby a deep learning model generates its own supervisory signal from the data, promises a scalable way to tackle the dramatically increasing size of real-world data sets without human annotation.
Jaderberg, B +5 more
openaire +2 more sources
Self-Supervised Transfer Learning from Natural Images for Sound Classification
Applied Sciences, 2021 We propose the implementation of transfer learning from natural images to audio-based images using self-supervised learning schemes. Through self-supervised learning, convolutional neural networks (CNNs) can learn the general representation of natural ...
Sungho Shin +4 more
doaj +1 more source
IEEE Access, 2023 Despite the remarkable progress of self-supervised learning (SSL), how self-supervised representations generalize to out-of-distribution data remains little understood.
Samira Zare, Hien Van Nguyen
doaj +1 more source
Homomorphic Self-Supervised Learning
CoRR, 2022 In this work, we observe that many existing self-supervised learning algorithms can be both unified and generalized when seen through the lens of equivariant representations. Specifically, we introduce a general framework we call Homomorphic Self-Supervised Learning, and theoretically show how it may subsume the use of input-augmentations provided an ...
T. Anderson Keller +2 more
openaire +3 more sources
Siamese-Network Based Signature Verification using Self Supervised Learning
IJCCS (Indonesian Journal of Computing and Cybernetics Systems), 2023 The use of signatures is often encountered in various public documents ranging from academic documents to business documents that are a sign that the existence of signatures is crucial in various administrative processes.
Muhammad Fawwaz Mayda, Aina Musdholifah
doaj +1 more source
A Cookbook of Self-Supervised Learning
CoRR, 2023 Self-supervised learning, dubbed the dark matter of intelligence, is a promising path to advance machine learning. Yet, much like cooking, training SSL methods is a delicate art with a high barrier to entry. While many components are familiar, successfully training a SSL method involves a dizzying set of choices from the pretext tasks to training hyper-
Randall Balestriero +18 more
openaire +2 more sources