Results 41 to 50 of about 10,370,937 (299)
Review of Self-supervised Learning Methods in Field of ECG [PDF]
Jisuanji kexue yu tansuoDeep learning has been widely applied in the field of electrocardiogram (ECG) signal analysis due to its powerful data representation capability. However, supervised methods require a large amount of labeled data, and ECG data annotation is typically ...
HAN Han, HUANG Xunhua, CHANG Huihui, FAN Haoyi, CHEN Peng, CHEN Jijia
doaj +1 more source
Comparing Learning Methodologies for Self-Supervised Audio-Visual Representation Learning
IEEE Access, 2022 In recent years, the machine learning community has devoted an increasing attention to self-supervised learning.The performance gap between supervised and self-supervised has become increasingly narrow in many computer vision applications. In this paper,
Hacene Terbouche +3 more
doaj +1 more source
Synergistic Self-supervised and Quantization Learning
, 2022 With the success of self-supervised learning (SSL), it has become a mainstream paradigm to fine-tune from self-supervised pretrained models to boost the performance on downstream tasks. However, we find that current SSL models suffer severe accuracy drops when performing low-bit quantization, prohibiting their deployment in resource-constrained ...
Yun-Hao Cao +4 more
openaire +3 more sources
Self-supervised Learning for Spinal MRIs [PDF]
, 2017 A significant proportion of patients scanned in a clinical setting have follow-up scans. We show in this work that such longitudinal scans alone can be used as a form of 'free' self-supervision for training a deep network. We demonstrate this self-supervised learning for the case of T2-weighted sagittal lumbar Magnetic Resonance Images (MRIs).
Jamaludin, A, Kadir, T, Zisserman, A
openaire +5 more sources
Reduce the Difficulty of Incremental Learning With Self-Supervised Learning
IEEE Access, 2021 Incremental learning requires a learning model to learn new tasks without forgetting the learned tasks continuously. However, when a deep learning model learns new tasks, it will catastrophically forget tasks it has learned before.
Linting Guan, Yan Wu
doaj +1 more source
Self-Supervised Learning :Video Clip Order Prediction with diffusion models [PDF]
, 2023 openIn recent years, neural networks have achieved incredible performance in computer vision applications like image classification and video identification due to the availability of powerful computational resources and vast amounts of data.
REPETTO, SARA
core
Self-Supervised Ranking for Representation Learning
CoRR, 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
Backdoor Attacks on Self-Supervised Learning
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use an inductive bias that random augmentations (e.g., random crops) of an image should produce similar embeddings ...
Aniruddha Saha +3 more
openaire +3 more sources
Boosting Self-Supervised Learning via Knowledge Transfer [PDF]
, 2018 In self-supervised learning, one trains a model to solve a so-called pretext task on a dataset without the need for human annotation. The main objective, however, is to transfer this model to a target domain and task.
Ananth Vinjimoor +7 more
core +2 more sources
Self-Supervised Learning with Swin Transformers
CoRR, 2021 We are witnessing a modeling shift from CNN to Transformers in computer vision. In this work, we present a self-supervised learning approach called MoBY, with Vision Transformers as its backbone architecture. The approach basically has no new inventions, which is combined from MoCo v2 and BYOL and tuned to achieve reasonably high accuracy on ImageNet ...
Zhenda Xie +6 more
openaire +3 more sources