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 4701–4750 of 5044 papers

TitleStatusHype
Rethinking Pre-Trained Feature Extractor Selection in Multiple Instance Learning for Whole Slide Image ClassificationCode0
Distributionally robust self-supervised learning for tabular dataCode0
Distilling Word Meaning in Context from Pre-trained Language ModelsCode0
Self-supervised learning for radio-astronomy source classification: a benchmarkCode0
Disentangled Modeling of Preferences and Social Influence for Group RecommendationCode0
Link Prediction with Non-Contrastive LearningCode0
Linear-Complexity Self-Supervised Learning for Speech ProcessingCode0
LightKG: Efficient Knowledge-Aware Recommendations with Simplified GNN ArchitectureCode0
Analysis of Self-Supervised Learning and Dimensionality Reduction Methods in Clustering-Based Active Learning for Speech Emotion RecognitionCode0
Discovering Visual Patterns in Art Collections with Spatially-consistent Feature LearningCode0
Leveraging Visual Supervision for Array-based Active Speaker Detection and LocalizationCode0
Representation Learning by Detecting Incorrect Location EmbeddingsCode0
Leveraging Pre-Trained Acoustic Feature Extractor For Affective Vocal Bursts TasksCode0
State Representation Learning Using an Unbalanced AtlasCode0
Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language ModelsCode0
Digging Into Self-Supervised Monocular Depth EstimationCode0
Self-supervised learning for skin cancer diagnosis with limited training dataCode0
Leveraging Joint Predictive Embedding and Bayesian Inference in Graph Self Supervised LearningCode0
Leveraging image captions for selective whole slide image annotationCode0
Self-Supervised Learning for Speech Enhancement through SynthesisCode0
Self-Supervised Learning in Multi-Task Graphs through Iterative Consensus ShiftCode0
Tracking Changing Probabilities via Dynamic LearnersCode0
STEdge: Self-training Edge Detection with Multi-layer Teaching and RegularizationCode0
DiffKillR: Killing and Recreating Diffeomorphisms for Cell Annotation in Dense Microscopy ImagesCode0
Leveraging Acoustic Images for Effective Self-Supervised Audio Representation LearningCode0
Leave No One Behind: Online Self-Supervised Self-Distillation for Sequential RecommendationCode0
Self-Supervised Learning for Time Series: A Review & Critique of FITSCode0
Learning Useful Representations of Recurrent Neural Network Weight MatricesCode0
STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural VideosCode0
Stereographic Spherical Sliced Wasserstein DistancesCode0
Self-supervised Learning for Video Correspondence FlowCode0
Self-Supervised Learning for Videos: A SurveyCode0
Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box ReconstructionCode0
Tracking Passengers and Baggage Items using Multiple Overhead Cameras at Security CheckpointsCode0
Analysing the Impact of Audio Quality on the Use of Naturalistic Long-Form Recordings for Infant-Directed Speech ResearchCode0
Learning to Reconstruct Signals From Binary MeasurementsCode0
Detection of Maternal and Fetal Stress from the Electrocardiogram with Self-Supervised Representation LearningCode0
Learning to Plan for Language Modeling from Unlabeled DataCode0
Self-Supervised Learning from Contrastive Mixtures for Personalized Speech EnhancementCode0
PLAD: Learning to Infer Shape Programs with Pseudo-Labels and Approximate DistributionsCode0
Self-Supervised Learning from Non-Object Centric Images with a Geometric Transformation Sensitive ArchitectureCode0
Visualizing and Understanding Contrastive LearningCode0
A Unified Framework for Foreground and Anonymization Area Segmentation in CT and MRI DataCode0
Self-Supervised Learning from Web Data for Multimodal RetrievalCode0
A deep cut into Split Federated Self-supervised LearningCode0
Z-SSMNet: Zonal-aware Self-supervised Mesh Network for Prostate Cancer Detection and Diagnosis with Bi-parametric MRICode0
StolenEncoder: Stealing Pre-trained Encoders in Self-supervised LearningCode0
Detecting Side Effects of Adverse Drug Reactions Through Drug-Drug Interactions Using Graph Neural Networks and Self-Supervised LearningCode0
Description-Enhanced Label Embedding Contrastive Learning for Text ClassificationCode0
MLEM: Generative and Contrastive Learning as Distinct Modalities for Event SequencesCode0
Show:102550
← PrevPage 95 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