Results 61 to 70 of about 546,017 (306)

Self-Supervised Ranking for Representation Learning

, 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, Diba, Ali, Tuytelaars, Tinne, Van Gool, Luc   +3 more
openaire   +3 more sources

Next‐generation proteomics improves lung cancer risk prediction

Molecular 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, Clara Frick, Ben Schöttker, Bernd Holleczek, Hermann Brenner   +4 more
wiley   +1 more source

How Well Do Self-Supervised Models Transfer to Medical Imaging?

Journal of Imaging, 2022
Self-supervised learning approaches have seen success transferring between similar medical imaging datasets, however there has been no large scale attempt to compare the transferability of self-supervised models against each other on medical images.
Jonah Anton, Liam Castelli, Mun Fai Chan, Mathilde Outters, Wan Hee Tang, Venus Cheung, Pancham Shukla, Rahee Walambe, Ketan Kotecha   +8 more
doaj   +1 more source

ShapeCodes: Self-Supervised Feature Learning by Lifting Views to Viewgrids

, 2018
We introduce an unsupervised feature learning approach that embeds 3D shape information into a single-view image representation. The main idea is a self-supervised training objective that, given only a single 2D image, requires all unseen views of the ...
D Jayaraman, D Jayaraman, GE Hinton, GE Hinton, J Masci, L Maaten van der, M Noroozi, M Tatarchenko, R Gao, R Girdhar, RN Shepard, T Zhou, TY Lin, Y Bengio   +13 more
core   +1 more source

Sharpness & Shift-Aware Self-Supervised Learning

, 2023
Self-supervised learning aims to extract meaningful features from unlabeled data for further downstream tasks. In this paper, we consider classification as a downstream task in phase 2 and develop rigorous theories to realize the factors that implicitly influence the general loss of this classification task.
Tran, Ngoc N., Duong, Son, Phan, Hoang, Pham, Tung, Phung, Dinh, Le, Trung   +5 more
openaire   +2 more sources

Genetic attenuation of ALDH1A1 increases metastatic potential and aggressiveness in colorectal cancer

Molecular Oncology, EarlyView.
Aldehyde dehydrogenase 1A1 (ALDH1A1) is a cancer stem cell marker in several malignancies. We established a novel epithelial cell line from rectal adenocarcinoma with unique overexpression of this enzyme. Genetic attenuation of ALDH1A1 led to increased invasive capacity and metastatic potential, the inhibition of proliferation activity, and ultimately ...
Martina Poturnajova, Zuzana Kozovska, Ondrej Pos, Kristina Pavlov, Sachin Gulati, Peter Makovicky, Kristina Jakic, Monika Burikova, Eva Sedlackova, Barbora Svitkova, Silvia Tyciakova, Vojtech Bystry, Nicolas Blavet, Boris Tichy, Matej Hrnciar, Jaroslav Budis, Miroslav Tomas, Peter Dubovan, Georgina Kolnikova, Veronika Repaska, Nikoleta Mojzesova, Eva Zomborska, Daniel Pindak, Michal Mego, Tomas Szemes, Miroslava Matuskova   +25 more
wiley   +1 more source

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

Remote 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

Self-Supervised Feature Learning by Learning to Spot Artifacts

, 2018
We introduce a novel self-supervised learning method based on adversarial training. Our objective is to train a discriminator network to distinguish real images from images with synthetic artifacts, and then to extract features from its intermediate ...
Favaro, Paolo, Jenni, Simon
core   +1 more source

Self-supervised learning

, 2020
This talk was presented for the Machine Learning Reading Group of the Wellcome Trust EPSRC for Interventional and Surgical Sciences of University College London, 11 February 2020.I gave an overview of self-supervised learning and some applications to computer vision and medical images.
openaire   +1 more source

Impact of a senior research thesis on students' perceptions of scientific inquiry in distinct student populations

FEBS Open Bio, EarlyView.
This study addressed how a senior research thesis is perceived by undergraduate students. It assessed students' perception of research skills, epistemological beliefs, and career goals in Biochemistry (science) and BDC (science‐business) students. Completing a thesis improved confidence in research skills, resilience, scientific identity, closed gender‐
Celeste Suart, Haley L. Zubyk, Michelle Ogrodnik, Caitlin E. Mullarkey, Felicia Vulcu   +4 more
wiley   +1 more source