SOTAVerified

Self-Supervised Learning

Self-Supervised Learning is proposed for utilizing unlabeled data with the success of supervised learning. Producing a dataset with good labels is expensive, while unlabeled data is being generated all the time. The motivation of Self-Supervised Learning is to make use of the large amount of unlabeled data. The main idea of Self-Supervised Learning is to generate the labels from unlabeled data, according to the structure or characteristics of the data itself, and then train on this unsupervised data in a supervised manner. Self-Supervised Learning is wildly used in representation learning to make a model learn the latent features of the data. This technique is often employed in computer vision, video processing and robot control.

Source: Self-supervised Point Set Local Descriptors for Point Cloud Registration

Image source: LeCun

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2451–2500 of 5044 papers

TitleStatusHype
SSL^2: Self-Supervised Learning meets Semi-Supervised Learning: Multiple Sclerosis Segmentation in 7T-MRI from large-scale 3T-MRI—0
Taming Contrast Maximization for Learning Sequential, Low-latency, Event-based Optical Flow—0
M3AE: Multimodal Representation Learning for Brain Tumor Segmentation with Missing ModalitiesCode1
Distortion-Disentangled Contrastive Learning—0
An Evaluation of Non-Contrastive Self-Supervised Learning for Federated Medical Image Analysis—0
Self-Supervised Learning for Group Equivariant Neural Networks—0
Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational ReasoningCode0
MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors—0
ST-KeyS: Self-Supervised Transformer for Keyword Spotting in Historical Handwritten Documents—0
Learning Efficient Coding of Natural Images with Maximum Manifold Capacity RepresentationsCode1
A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS—0
A Self-Correcting Sequential RecommenderCode1
PixMIM: Rethinking Pixel Reconstruction in Masked Image ModelingCode0
Self-Supervised Learning for Place Representation Generalization across Appearance Changes—0
Self-supervised Learning for Gastrointestinal Pathologies Endoscopy Image Classification with Triplet Loss—0
Contrastive Hierarchical ClusteringCode1
Zero-Shot Self-Supervised Joint Temporal Image and Sensitivity Map Reconstruction via Linear Latent SpaceCode0
TRUSformer: Improving Prostate Cancer Detection from Micro-Ultrasound Using Attention and Self-SupervisionCode0
Towards Democratizing Joint-Embedding Self-Supervised LearningCode2
Single-photon Image Super-resolution via Self-supervised Learning—0
Exploring Self-Supervised Representation Learning For Low-Resource Medical Image AnalysisCode0
Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition ProblemsCode1
Evolutionary Augmentation Policy Optimization for Self-supervised Learning—0
ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud CompletionCode1
Rethinking the Effect of Data Augmentation in Adversarial Contrastive LearningCode1
Heterogeneous Graph Contrastive Learning for RecommendationCode1
Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive LearningCode1
ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations—0
Benchmarking Self-Supervised Contrastive Learning Methods for Image-Based Plant PhenotypingCode0
Quality-aware Pre-trained Models for Blind Image Quality Assessment—0
Can representation learning for multimodal image registration be improved by supervision of intermediate layers?—0
ParrotTTS: Text-to-Speech synthesis by exploiting self-supervised representations—0
An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization—0
Mosaic Representation Learning for Self-supervised Visual Pre-trainingCode1
Temporal Coherent Test-Time Optimization for Robust Video Classification—0
Remote Sensing Scene Classification with Masked Image Modeling (MIM)—0
A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking—0
SSL-QALAS: Self-Supervised Learning for Rapid Multiparameter Estimation in Quantitative MRI Using 3D-QALAS—0
Internet Explorer: Targeted Representation Learning on the Open WebCode1
MPS-AMS: Masked Patches Selection and Adaptive Masking Strategy Based Self-Supervised Medical Image Segmentation—0
Revisiting Self-Training with Regularized Pseudo-Labeling for Tabular Data—0
A Self-Supervised Learning-based Approach to Clustering Multivariate Time-Series Data with Missing Values (SLAC-Time): An Application to TBI Phenotyping—0
EDMAE: An Efficient Decoupled Masked Autoencoder for Standard View Identification in Pediatric Echocardiography—0
Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training—0
Medical visual question answering using joint self-supervised learning—0
Amortised Invariance Learning for Contrastive Self-SupervisionCode0
Hiding Data Helps: On the Benefits of Masking for Sparse CodingCode0
Improving Adaptive Conformal Prediction Using Self-Supervised LearningCode1
ProsAudit, a prosodic benchmark for self-supervised speech models—0
Random Teachers are Good TeachersCode0
Show:102550
← PrevPage 50 of 101Next →
All datasetsDABSSTL-10CIFAR10cifar100ImageNet-100 (TEMI Split)TinyImageNetCIFAR-10CIFAR-100CREMA-DTiny ImageNet

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Pretraining: NoneImages & Text57.5—Unverified
2Pretraining: ShEDImages & Text54.3—Unverified
3Pretraining: e-MixImages & Text48.9—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50Accuracy91.7—Unverified
2ResNet18Accuracy91.02—Unverified
3MV-MRAccuracy89.67—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy93.89—Unverified
2ResNet18average top-1 classification accuracy92.58—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy72.51—Unverified
2ResNet18average top-1 classification accuracy69.31—Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet50)Top-1 Accuracy82.64—Unverified
2CorInfomax (ResNet18)Top-1 Accuracy80.48—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy51.84—Unverified
2ResNet18average top-1 classification accuracy51.67—Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet18)Top-1 Accuracy93.18—Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet18)Top-1 Accuracy71.61—Unverified
#ModelMetricClaimedVerifiedStatus
1Hybrid BYOL-S/CvTAccuracy67.2—Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet50)Top-1 Accuracy54.86—Unverified