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

Showing 14511500 of 5044 papers

TitleStatusHype
BAL: Balancing Diversity and Novelty for Active LearningCode0
DDxT: Deep Generative Transformer Models for Differential DiagnosisCode0
Revisiting and Benchmarking Graph Autoencoders: A Contrastive Learning PerspectiveCode0
DDA: Dimensionality Driven Augmentation Search for Contrastive Learning in Laparoscopic SurgeryCode0
Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic DecompositionCode0
Rethinking The Uniformity Metric in Self-Supervised LearningCode0
An attention-based backend allowing efficient fine-tuning of transformer models for speaker verificationCode0
About Explicit Variance Minimization: Training Neural Networks for Medical Imaging With Limited Data AnnotationsCode0
Rethinking Polyp Segmentation from an Out-of-Distribution PerspectiveCode0
Data-Efficient Sleep Staging with Synthetic Time Series PretrainingCode0
Rethinking Graph Masked Autoencoders through Alignment and UniformityCode0
Data Efficient Contrastive Learning in Histopathology using Active SamplingCode0
Rethinking Temperature in Graph Contrastive LearningCode0
Data Augmentation is a Hyperparameter: Cherry-picked Self-Supervision for Unsupervised Anomaly Detection is Creating the Illusion of SuccessCode0
Rethinking CNN-Based Pansharpening: Guided Colorization of Panchromatic Images via GANsCode0
Rethinking Contrastive Learning in Session-based RecommendationCode0
Rethinking and Simplifying Bootstrapped Graph LatentsCode0
Ablation study of self-supervised learning for image classificationCode0
RetFiner: A Vision-Language Refinement Scheme for Retinal Foundation ModelsCode0
Self-supervised Label Augmentation via Input TransformationsCode0
Representation Learning of Lab Values via Masked AutoEncoderCode0
Quantifying Representation Reliability in Self-Supervised Learning ModelsCode0
Reproducing BowNet: Learning Representations by Predicting Bags of Visual WordsCode0
Rethinking Generalizability and Discriminability of Self-Supervised Learning from Evolutionary Game Theory PerspectiveCode0
Replay-free Online Continual Learning with Self-Supervised MultiPatchesCode0
Analyzing Data-Centric Properties for Graph Contrastive LearningCode0
Region-of-interest guided Supervoxel Inpainting for Self-supervisionCode0
Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class DiscoveryCode0
RegExplainer: Generating Explanations for Graph Neural Networks in Regression TasksCode0
AV-DTEC: Self-Supervised Audio-Visual Fusion for Drone Trajectory Estimation and ClassificationCode0
Re-entry Prediction for Online Conversations via Self-Supervised LearningCode0
Relating Human Perception of Musicality to Prediction in a Predictive Coding ModelCode0
AVATAR: Adversarial self-superVised domain Adaptation network for TARget domainCode0
AdaProj: Adaptively Scaled Angular Margin Subspace Projections for Anomalous Sound Detection with Auxiliary Classification TasksCode0
Random Teachers are Good TeachersCode0
Rapid Wildfire Hotspot Detection Using Self-Supervised Learning on Temporal Remote Sensing DataCode0
Cross-Skeleton Interaction Graph Aggregation Network for Representation Learning of Mouse Social BehaviourCode0
Analysis of Self-Supervised Learning and Dimensionality Reduction Methods in Clustering-Based Active Learning for Speech Emotion RecognitionCode0
Quantitative Imaging Principles Improves Medical Image LearningCode0
Analysing the Impact of Audio Quality on the Use of Naturalistic Long-Form Recordings for Infant-Directed Speech ResearchCode0
Cross-Modal Self-Supervised Learning with Effective Contrastive Units for LiDAR Point CloudsCode0
Quantile-based Maximum Likelihood Training for Outlier DetectionCode0
CrossMoCo: Multi-modal Momentum Contrastive Learning for Point CloudCode0
Cross-Lingual Speech Emotion Recognition: Humans vs. Self-Supervised ModelsCode0
PU-Ray: Domain-Independent Point Cloud Upsampling via Ray Marching on Neural Implicit SurfaceCode0
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?Code0
PSSL: Self-supervised Learning for Personalized Search with Contrastive SamplingCode0
PRSNet: A Masked Self-Supervised Learning Pedestrian Re-Identification MethodCode0
Automatic separation of laminar-turbulent flows on aircraft wings and stabilisers via adaptive attention butterfly networkCode0
PSA-SSL: Pose and Size-aware Self-Supervised Learning on LiDAR Point CloudsCode0
Show:102550
← PrevPage 30 of 101Next →

Benchmark Results

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