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 1301–1350 of 5044 papers

TitleStatusHype
Electrocardio Panorama: Synthesizing New ECG Views with Self-supervisionCode1
Embedding in Recommender Systems: A SurveyCode1
Giga-SSL: Self-Supervised Learning for Gigapixel ImagesCode1
On the Transferability of Large-Scale Self-Supervision to Few-Shot Audio ClassificationCode1
On the Utility of Self-supervised Models for Prosody-related TasksCode1
Open-vocabulary Semantic Segmentation with Frozen Vision-Language ModelsCode1
Orchestra: Unsupervised Federated Learning via Globally Consistent ClusteringCode1
GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-TrainingCode1
Emerging Properties in Self-Supervised Vision TransformersCode1
Overcoming Language Priors with Self-supervised Learning for Visual Question AnsweringCode1
Benchmarking Embedding Aggregation Methods in Computational Pathology: A Clinical Data PerspectiveCode1
Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning​Code1
GestSync: Determining who is speaking without a talking headCode1
Global Contrast Masked Autoencoders Are Powerful Pathological Representation LearnersCode1
GenSelfDiff-HIS: Generative Self-Supervision Using Diffusion for Histopathological Image SegmentationCode1
Generative and Contrastive Self-Supervised Learning for Graph Anomaly DetectionCode1
GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised LearningCode1
PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-IdentificationCode1
Benchmarking Detection Transfer Learning with Vision TransformersCode1
Deeper into Self-Supervised Monocular Indoor Depth EstimationCode1
Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised trainingCode1
Point2Vec for Self-Supervised Representation Learning on Point CloudsCode1
A Review on Self-Supervised Learning for Time Series Anomaly Detection: Recent Advances and Open ChallengesCode1
PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud VideosCode1
Generalizing Event-Based Motion Deblurring in Real-World ScenariosCode1
Empowering Collaborative Filtering with Principled Adversarial Contrastive LossCode1
Geography-Aware Self-Supervised LearningCode1
Gloss-free Sign Language Translation: Improving from Visual-Language PretrainingCode1
Post-training for Deepfake Speech DetectionCode1
EnCodecMAE: Leveraging neural codecs for universal audio representation learningCode1
Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and ReasoningCode1
Predicting the Best of N Visual TrackersCode1
COSMOS: Catching Out-of-Context Misinformation with Self-Supervised LearningCode1
Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse ContextsCode1
Adversarial Self-Supervised Contrastive LearningCode1
Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information BottleneckCode1
Pretraining Language Models to Ponder in Continuous SpaceCode1
Pre-training Molecular Graph Representation with 3D GeometryCode1
Primitive Geometry Segment Pre-training for 3D Medical Image SegmentationCode1
PRNet: Self-Supervised Learning for Partial-to-Partial RegistrationCode1
End-to-end Multi-modal Video Temporal GroundingCode1
End-to-end Multiple Instance Learning with Gradient AccumulationCode1
What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable InsightsCode1
GAMC: An Unsupervised Method for Fake News Detection using Graph Autoencoder with MaskingCode1
Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm PerformanceCode1
Enhanced Masked Image Modeling to Avoid Model Collapse on Multi-modal MRI DatasetsCode1
Gaining Insight into SARS-CoV-2 Infection and COVID-19 Severity Using Self-supervised Edge Features and Graph Neural NetworksCode1
Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete LabelsCode1
CCGL: Contrastive Cascade Graph LearningCode1
GATE: Graph CCA for Temporal SElf-supervised Learning for Label-efficient fMRI AnalysisCode1
Show:102550
← PrevPage 27 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