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 2001–2050 of 5044 papers

TitleStatusHype
CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent MaskingCode1
Foundational Models for Fault Diagnosis of Electrical Motors—0
Mispronunciation detection using self-supervised speech representationsCode0
Self-Supervised Learning of Gait-Based Biomarkers—0
Motion Degeneracy in Self-supervised Learning of Elevation Angle Estimation for 2D Forward-Looking Sonar—0
MUSE: Multi-View Contrastive Learning for Heterophilic Graphs—0
HandMIM: Pose-Aware Self-Supervised Learning for 3D Hand Mesh Estimation—0
AC-Norm: Effective Tuning for Medical Image Analysis via Affine Collaborative NormalizationCode0
BOURNE: Bootstrapped Self-supervised Learning Framework for Unified Graph Anomaly Detection—0
Self-Supervised Learning for Improved Synthetic Aperture Sonar Target Recognition—0
Gloss-free Sign Language Translation: Improving from Visual-Language PretrainingCode1
GaitMorph: Transforming Gait by Optimally Transporting Discrete Codes—0
vox2vec: A Framework for Self-supervised Contrastive Learning of Voxel-level Representations in Medical ImagesCode1
Mixture of Self-Supervised LearningCode0
Fluorescent Neuronal Cells v2: Multi-Task, Multi-Format Annotations for Deep Learning in Microscopy—0
Speech representation learning: Learning bidirectional encoders with single-view, multi-view, and multi-task methods—0
How to Scale Your EMA—0
SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image SegmentationCode1
MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features—0
Learning Navigational Visual Representations with Semantic Map SupervisionCode1
Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation—0
Self-Supervised Learning for Audio-Based Emotion Recognition—0
Downstream-agnostic Adversarial ExamplesCode1
Contrastive Self-Supervised Learning Based Approach for Patient Similarity: A Case Study on Atrial Fibrillation Detection from PPG SignalCode0
Hallucination Improves the Performance of Unsupervised Visual Representation Learning—0
Zero-note samba: Self-supervised beat trackingCode1
Building3D: An Urban-Scale Dataset and Benchmarks for Learning Roof Structures from Point Clouds—0
Self2Self+: Single-Image Denoising with Self-Supervised Learning and Image Quality Assessment LossCode1
SLPD: Slide-level Prototypical Distillation for WSIsCode0
Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series—0
Revisiting Fine-Tuning Strategies for Self-supervised Medical Imaging Analysis—0
Language-based Action Concept Spaces Improve Video Self-Supervised Learning—0
The Role of Entropy and Reconstruction in Multi-View Self-Supervised LearningCode1
MASR: Multi-label Aware Speech Representation—0
PASTA: Pretrained Action-State Transformer Agents—0
Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop FeedbackCode1
Self-Supervised Learning for WiFi CSI-Based Human Activity Recognition: A Systematic Study—0
CSSL-RHA: Contrastive Self-Supervised Learning for Robust Handwriting Authentication—0
Towards the Sparseness of Projection Head in Self-Supervised Learning—0
MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook AssignmentsCode1
Systematic comparison of semi-supervised and self-supervised learning for medical image classificationCode1
For One-Shot Decoding: Self-supervised Deep Learning-Based Polar Decoder—0
Model Adaptation for ASR in low-resource Indian Languages—0
Audio-Visual Speech Enhancement Using Self-supervised Learning to Improve Speech Intelligibility in Cochlear Implant Simulations—0
RegExplainer: Generating Explanations for Graph Neural Networks in Regression TasksCode0
Does Double Descent Occur in Self-Supervised Learning?Code0
FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object SegmentationCode1
L-DAWA: Layer-wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation LearningCode1
Multi-view self-supervised learning for multivariate variable-channel time seriesCode0
Leveraging Pretrained ASR Encoders for Effective and Efficient End-to-End Speech Intent Classification and Slot Filling—0
Show:102550
← PrevPage 41 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