Results 51 to 60 of about 549,786 (309)

Self-Supervised Video Similarity Learning

open access: yes2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023
We introduce S$^2$VS, a video similarity learning approach with self-supervision. Self-Supervised Learning (SSL) is typically used to train deep models on a proxy task so as to have strong transferability on target tasks after fine-tuning. Here, in contrast to prior work, SSL is used to perform video similarity learning and address multiple retrieval ...
Kordopatis-Zilos, Giorgos   +5 more
openaire   +2 more sources

Reblur2Deblur: Deblurring Videos via Self-Supervised Learning

open access: yes, 2018
Motion blur is a fundamental problem in computer vision as it impacts image quality and hinders inference. Traditional deblurring algorithms leverage the physics of the image formation model and use hand-crafted priors: they usually produce results that ...
Chen, Huaijin   +5 more
core   +1 more source

Self-Supervised Representation Learning for Ultrasound Video

open access: yes2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), 2020
Recent advances in deep learning have achieved promising performance for medical image analysis, while in most cases ground-truth annotations from human experts are necessary to train the deep model. In practice, such annotations are expensive to collect and can be scarce for medical imaging applications.
Jaio, J   +4 more
openaire   +4 more sources

Self-Supervised Adversarial Imitation Learning

open access: yes2023 International Joint Conference on Neural Networks (IJCNN), 2023
This paper has been accepted in the International Joint Conference on Neural Networks (IJCNN ...
Monteiro, Juarez   +3 more
openaire   +2 more sources

To Compress or Not to Compress—Self-Supervised Learning and Information Theory: A Review

open access: yesEntropy
Deep 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   +1 more source

Self-Supervised EEG Emotion Recognition Models Based on CNN

open access: yesIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023
Emotion plays crucial roles in human life. Recently, emotion classification from electroencephalogram (EEG) signal has attracted attention by researchers due to the rapid development of brain computer interface (BCI) techniques and machine learning ...
Xingyi Wang   +5 more
doaj   +1 more source

Transitive Invariance for Self-supervised Visual Representation Learning

open access: yes, 2017
Learning visual representations with self-supervised learning has become popular in computer vision. The idea is to design auxiliary tasks where labels are free to obtain.
Gupta, Abhinav   +2 more
core   +1 more source

Self-Supervised Ranking for Representation Learning

open access: yes, 2020
We present a new framework for self-supervised representation learning by formulating it as a ranking problem in an image retrieval context on a large number of random views (augmentations) obtained from images. Our work is based on two intuitions: first, a good representation of images must yield a high-quality image ranking in a retrieval task ...
Varamesh, Ali   +3 more
openaire   +3 more sources

Next‐generation proteomics improves lung cancer risk prediction

open access: yesMolecular Oncology, EarlyView.
This is one of very few studies that used prediagnostic blood samples from participants of two large population‐based cohorts. We identified, evaluated, and validated an innovative protein marker model that outperformed an established risk prediction model and criteria employed by low‐dose computed tomography in lung cancer screening trials.
Megha Bhardwaj   +4 more
wiley   +1 more source

Ship Detection in Sentinel 2 Multi-Spectral Images with Self-Supervised Learning

open access: yesRemote Sensing, 2021
Automatic ship detection provides an essential function towards maritime domain awareness for security or economic monitoring purposes. This work presents an approach for training a deep learning ship detector in Sentinel-2 multi-spectral images with few
Alina Ciocarlan, Andrei Stoian
doaj   +1 more source

Home - About - Disclaimer - Privacy