28 papers · ranked by Valyu relevance
Shih-Cheng Huang, Anuj Pareek, Malte Jensen, Matthew P. Lungren + 2 more
'Serena Yeung' 'Akshay S. Chaudhari'] Advancements in deep learning and computer vision provide promising solutions for medical image analysis, potentially improving healthcare and patient outcomes. However, the prevailing paradigm of training deep learning models requires large quantities of labeled training data…
Taoran Sheng, Manfred Huber, Giovanni Saggio
Human activity recognition (HAR) using wearable sensors has advanced through various machine learning paradigms, each with inherent trade-offs between performance and labeling requirements. While fully supervised techniques achieve high accuracy, they demand extensive labeled datasets that are costly to obtain.…
Kevin G. Montero Quispe, Daniel M. S. Utyiama, Eulanda M. dos Santos, Horácio A. B. F. Oliveira + 2 more
'Horácio A. B. F. Oliveira' 'Eduardo J. P. Souto' 'Mario Munoz-Organero'] The use of machine learning (ML) techniques in affective computing applications focuses on improving the user experience in emotion recognition. The collection of input data (e.g., physiological signals), together with expert annotations are part…
Dimitris Spathis, Ignacio Perez-Pozuelo, Laia Marques-Fernandez, Cecilia Mascolo
Title: Summary Medicine is undergoing an unprecedented digital transformation, as massive amounts of health data are being produced, gathered, and curated, ranging from in-hospital (e.g., intensive care unit [ICU]) to person-generated data (wearables). Annotating all these data for training purposes in order to feed to…
Markus Marks, Manuel Knott, Neehar Kondapaneni, Elijah Cole + 3 more
'Thijs Defraeye' 'Fernando Perez-Cruz' 'Pietro Perona'] Self-supervised learning (SSL) is a machine learning approach where the data itself provides supervision, eliminating the need for external labels. The model is forced to learn about the data’s inherent structure or context by solving a pretext task. With SSL…
Asaki Kataoka, Yoshihiro Nagano, Masafumi Oizumi
Recent advances in self-supervised learning have attracted significant attention from both machine learning and neuroscience. This is primarily because self-supervised methods do not require annotated supervisory information, making them applicable to training artificial networks without relying on large amounts of…
Steven M. Peterson, Rajesh P. N. Rao, Bingni W. Brunton
Recent advances in neural decoding have accelerated the development of brain-computer interfaces aimed at assisting users with everyday tasks such as speaking, walking, and manipulating objects. However, current approaches for training neural decoders commonly require large quantities of labeled data, which can be…
Yinjun Jia, Shuaishuai Li, Xuan Guo, Junqiang Hu + 2 more
Fast and accurately characterizing animal behaviors is crucial for neuroscience research. Deep learning models are efficiently used in laboratories for behavior analysis. However, it has not been achieved to use a fully unsupervised method to extract comprehensive and discriminative features directly from raw behavior…
Attaullah Sahito, Eibe Frank, Bernhard Pfahringer
> Abstract. Self-training is a simple semi-supervised learning approach: Unlabelled examples that attract high-confidence predictions are labelled with their predictions and added to the training set, with this process being repeated multiple times. Recently, self-supervision—learning without manual supervision by…
Gabriel Díaz, Billy Peralta, Luis Caro, Orietta Nicolis + 1 more
'Gastone C. Castellani'] Automatic recognition of visual objects using a deep learning approach has been successfully applied to multiple areas. However, deep learning techniques require a large amount of labeled data, which is usually expensive to obtain. An alternative is to use semi-supervised models, such as…
Kevin Kermani Nejad, Paul Anastasiades, Loreen Hertäg, Rui Ponte Costa
The neocortex constructs an internal representation of the world, but the underlying circuitry and computational principles remain unclear. Inspired by self-supervised learning algorithms, we introduce a computational model wherein layer 2/3 (L2/3) learns to predict incoming sensory stimuli by comparing previous…
Jonah Anton, Liam Castelli, Mun Fai Chan, Mathilde Outters + 10 more
'Wan Hee Tang' 'Venus Cheung' 'Pancham Shukla' 'Rahee Walambe' 'Ketan Kotecha' 'Cecilia Di Ruberto' 'Alessandro Stefano' 'Albert Comelli' 'Lorenzo Putzu' 'Andrea Loddo'] Self-supervised learning approaches have seen success transferring between similar medical imaging datasets, however there has been no large scale…
Hang Hu, Jyothsna Padmakumar Bindu, Julia Laskin
Mass spectrometry imaging (MSI) is widely used for the label-free molecular mapping of biological samples. The identification of co-localized molecules in MSI data is crucial to the understanding of biochemical pathways. However, complex MSI data are too large for manual annotation but too small for training deep…
Huimin Peng
This paper briefly reviews the connections between meta-learning and self-supervised learning. Meta-learning can be applied to improve model generalization capability and to construct general AI algorithms. Self-supervised learning utilizes self-supervision from original data and extracts higher-level generalizable…
Qing Chang, Junran Peng, Lingxie Xie, Jiajun Sun + 3 more
'Qi Tian' 'Zhaoxiang Zhang'] Qing Chang 1,3,4,5 Junran Peng 2 Lingxi Xie 2 Jiajun Sun 1,3,4,5 Haoran Yin 1,3,4,5 Qi Tian 2 Zhaoxiang Zhang*1,3,4,5,6 1University of Chinese Academy of Sciences, 2Huawei Inc. 3 Institute of Automation, Chinese Academy of Sciences 4National Laboratory of Pattern Recognition 5Center for…
Hilal AlQuabeh, Ameera Bawazeer, Abdulateef Alhashmi
Data labeling in supervised learning is considered an expensive and infeasible tool in some conditions. The self-supervised learning method is proposed to tackle the learning effectiveness with fewer labeled data, however, there is a lack of confidence in the size of labeled data needed to achieve adequate results.…
Daniel Otero, Rafael Mateus
Sewerage infrastructure is among the most expensive modern investments requiring time-intensive manual inspections by qualified personnel. Our study addresses the need for automated solutions without relying on large amounts of labeled data. We propose a novel application of Self-Supervised Learning (SSL) for sewer…
Yi Wang, Conrad M Albrecht, Nassim Ait Ali Braham, Lichao Mou + 1 more
'Xiao Xiang Zhu'] Abstract—In deep learning research, self-supervised learning (SSL) has received great attention triggering interest within both the computer vision and remote sensing communities. While there has been a big success in computer vision, most of the potential of SSL in the domain of earth observation…
Rahil Gholamipoor, Nima Rafiee, Markus Kollmann
X-ray images have been widely used for medical diagnoses of cardiothoracic and pulmonary abnormalities due to its noninvasiveness. Advancement in computer-aided diagnostic technologies, such as deep supervised methods, can help radiologists with a reliable early treatment and reduce diagnosis time. Nevertheless, these…
Yao-Hung Hubert Tsai, Yue Wu, Ruslan Salakhutdinov, Louis‐Philippe Morency
'Louis‐Philippe Morency'] As a subset of unsupervised representation learning, self-supervised representation learning adopts self-defined signals as supervision and uses the learned representation for downstream tasks, such as object detection and image captioning. Many proposed approaches for self-supervised learning…
Matthew R Whiteway, Evan S Schaffer, Anqi Wu, E Kelly Buchanan + 3 more
A popular approach to quantifying animal behavior from video data is through discrete behavioral segmentation, wherein video frames are labeled as containing one or more behavior classes such as walking or grooming. Sequence models learn to map behavioral features extracted from video frames to discrete behaviors, and…
Hongyang Dong, Simon D.M. Jacques, Keith T. Butler, Olof Gutowski + 4 more
In this study, we introduce a method designed to eliminate parallax artefacts present in Xray powder diffraction computed tomography data acquired from large samples. These parallax artefacts manifest as artificial peak shifting, broadening and splitting, leading to inaccurate physicochemical information, such as…
Authors not listed
Machine learning approaches for conceptualizing and designing in silico compounds have attracted significant attention. However, the applicability of these compounds is often challenged by synthetic viability and cost-effectiveness. Researchers introduced proxy-scores, known as synthethic accessiblity scoring, to…
Jong-Yeup Kim, Gayrat Tangriberganov, Woochul Jung, Dae Sung Kim + 3 more
In order to reach better performance in visual representation learning from image or video dataset, huge amount of annotated data are on demand. However, collecting and annotating large-scale datasets are costly and time-consuming tasks. Especially, in a domain like medical, it is hard to access patient images because…
Hongyang Dong, Simon D.M. Jacques, Winfried Kockelmann, Stephen W. T. Price + 10 more
Hongyang Dong 3 , Simon D.M. Jacques 1 , Winfried Kockelmann 4 , Stephen W. T. Price 1 , Robert Emberson 5 , Dorota Matras 6,7 , Yaroslav Odarchenko 1 , Vesna Middelkoop 10 , Athanasios Giokaris 1 , Olof Gutowski 8 , Ann-Christin Dippel 8 , Martin v. Zimmermann 8 , Andrew M. Beale 3 , Keith T. Butler 9 , Antonis…
Authors not listed
nDTomo is a Python-based software suite for the simulation, reconstruction and analysis of X-ray chemical imaging and computed tomography data. It provides a collection of Python function-based tools designed for accessibility and education as well as a graphical user interface (GUI). Prioritising transparency and ease…
Ross Irwin, Spyridon Dimitriadis, Jiazhen He, Esben Bjerrum
Transformer models coupled with Simplified Molecular Line Entry System (SMILES) have recently proven to be a powerful combination for solving challenges in cheminformatics. These models, however, are often developed specifically for a single application and can be very resource-intensive to train. In this work we…
David Buterez, Jon Paul Janet, Steven Kiddle, Pietro Liò
We investigate the potential of graph neural networks for transfer learning and improving molecular property prediction on sparse and expensive to acquire high-fidelity data by leveraging low-fidelity measurements as an inexpensive proxy for a targeted property ofinterest. This problem arises in discovery processes…