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 10511100 of 5044 papers

TitleStatusHype
Mitigating Memorization of Noisy Labels via Regularization between RepresentationsCode1
Unsupervised Representation Learning for Binary Networks by Joint Classifier LearningCode1
Self-Supervised Learning by Estimating Twin Class DistributionsCode1
Decoupled Contrastive LearningCode1
Relative Molecule Self-Attention TransformerCode1
UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-TrainingCode1
K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and SyllablesCode1
Self-supervised Learning is More Robust to Dataset ImbalanceCode1
SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation LearningCode1
3D Infomax improves GNNs for Molecular Property PredictionCode1
Self-supervised Speaker Recognition with Loss-gated LearningCode1
Pre-training Molecular Graph Representation with 3D GeometryCode1
Self-Supervised Generative Style Transfer for One-Shot Medical Image SegmentationCode1
Motif-based Graph Self-Supervised Learning for Molecular Property PredictionCode1
Consistent Explanations by Contrastive LearningCode1
DualNet: Continual Learning, Fast and SlowCode1
Noise2Recon: Enabling Joint MRI Reconstruction and Denoising with Semi-Supervised and Self-Supervised LearningCode1
Mining for Strong Gravitational Lenses with Self-supervised LearningCode1
Self-Supervised Learning for MRI Reconstruction with a Parallel Network Training FrameworkCode1
Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised LearningCode1
Self-supervised learning methods and applications in medical imaging analysis: A surveyCode1
Self-supervised Contrastive Learning for EEG-based Sleep StagingCode1
Reconstructing occluded Elevation Information in Terrain Maps with Self-supervised LearningCode1
Seeking an Optimal Approach for Computer-Aided Pulmonary Embolism DetectionCode1
TEASEL: A Transformer-Based Speech-Prefixed Language ModelCode1
Spatio-Temporal Recurrent Networks for Event-Based Optical Flow EstimationCode1
Topic-Aware Contrastive Learning for Abstractive Dialogue SummarizationCode1
Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse ContextsCode1
Self-supervised Pseudo Multi-class Pre-training for Unsupervised Anomaly Detection and Segmentation in Medical ImagesCode1
Self-supervised Point Cloud Representation Learning via Separating Mixed ShapesCode1
ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasetsCode1
Digging into Uncertainty in Self-supervised Multi-view StereoCode1
MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous DrivingCode1
Self-Supervised Graph Co-Training for Session-based RecommendationCode1
Generative and Contrastive Self-Supervised Learning for Graph Anomaly DetectionCode1
Jointly Learnable Data Augmentations for Self-Supervised GNNsCode1
Self-Rule to Multi-Adapt: Generalized Multi-source Feature Learning Using Unsupervised Domain Adaptation for Colorectal Cancer Tissue DetectionCode1
Improving Self-supervised Learning with Hardness-aware Dynamic Curriculum Learning: An Application to Digital PathologyCode1
Contrastive Self-supervised Sequential Recommendation with Robust AugmentationCode1
Dual Path Learning for Domain Adaptation of Semantic SegmentationCode1
Is Pseudo-Lidar needed for Monocular 3D Object detection?Code1
AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language ProcessingCode1
Representation Learning for Remote Sensing: An Unsupervised Sensor Fusion ApproachCode1
Skeleton-Contrastive 3D Action Representation LearningCode1
Improving Contrastive Learning by Visualizing Feature TransformationCode1
Co-learning: Learning from Noisy Labels with Self-supervisionCode1
BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised LearningCode1
Object-aware Contrastive Learning for Debiased Scene RepresentationCode1
Self-Supervised Learning for Fine-Grained Image ClassificationCode1
CCGL: Contrastive Cascade Graph LearningCode1
Show:102550
← PrevPage 22 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