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 1501–1550 of 5044 papers

TitleStatusHype
Cross-domain Contrastive Learning for Unsupervised Domain AdaptationCode0
AdaCrossNet: Adaptive Dynamic Loss Weighting for Cross-Modal Contrastive Point Cloud LearningCode0
Rethinking and Simplifying Bootstrapped Graph LatentsCode0
Revisiting and Benchmarking Graph Autoencoders: A Contrastive Learning PerspectiveCode0
Cross and Learn: Cross-Modal Self-SupervisionCode0
Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class DiscoveryCode0
CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised LearningCode0
Region-of-interest guided Supervoxel Inpainting for Self-supervisionCode0
Credal Self-Supervised LearningCode0
RegExplainer: Generating Explanations for Graph Neural Networks in Regression TasksCode0
Relating Human Perception of Musicality to Prediction in a Predictive Coding ModelCode0
Amortised Invariance Learning for Contrastive Self-SupervisionCode0
Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship AttributionCode0
Re-entry Prediction for Online Conversations via Self-Supervised LearningCode0
COSTAR: Improved Temporal Counterfactual Estimation with Self-Supervised LearningCode0
Rapid Wildfire Hotspot Detection Using Self-Supervised Learning on Temporal Remote Sensing DataCode0
CoSeg: Cognitively Inspired Unsupervised Generic Event SegmentationCode0
Cooperative Knowledge Distillation: A Learner Agnostic ApproachCode0
Random Teachers are Good TeachersCode0
A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware CapabilityCode0
A Unified Framework for Foreground and Anonymization Area Segmentation in CT and MRI DataCode0
Quantile-based Maximum Likelihood Training for Outlier DetectionCode0
Quantitative Imaging Principles Improves Medical Image LearningCode0
A Unified and Scalable Membership Inference Method for Visual Self-supervised Encoder via Part-aware CapabilityCode0
PU-Ray: Domain-Independent Point Cloud Upsampling via Ray Marching on Neural Implicit SurfaceCode0
Contrastive Self-supervised Neural Architecture SearchCode0
PSA-SSL: Pose and Size-aware Self-Supervised Learning on LiDAR Point CloudsCode0
Pseudolabel guided pixels contrast for domain adaptive semantic segmentationCode0
PRSNet: A Masked Self-Supervised Learning Pedestrian Re-Identification MethodCode0
PSSL: Self-supervised Learning for Personalized Search with Contrastive SamplingCode0
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?Code0
Contrastive Self-Supervised Learning for Wireless Power ControlCode0
ProtoX: Explaining a Reinforcement Learning Agent via PrototypingCode0
Contrastive Self-Supervised Learning Based Approach for Patient Similarity: A Case Study on Atrial Fibrillation Detection from PPG SignalCode0
Augmentation-aware Self-supervised Learning with Conditioned ProjectorCode0
All models are wrong, some are useful: Model Selection with Limited LabelsCode0
Augmentation Component Analysis: Modeling Similarity via the Augmentation OverlapsCode0
Privacy-Preserving Models for Legal Natural Language ProcessingCode0
All4One: Symbiotic Neighbour Contrastive Learning via Self-Attention and Redundancy ReductionCode0
Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement LearningCode0
Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality RegularizationCode0
Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised LearningCode0
AAG: Self-Supervised Representation Learning by Auxiliary Augmentation with GNT-Xent LossCode0
Pretraining ECG Data with Adversarial Masking Improves Model Generalizability for Data-Scarce TasksCode0
Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning ModelsCode0
Audio Barlow Twins: Self-Supervised Audio Representation LearningCode0
Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio RepresentationCode0
Preserving Modality Structure Improves Multi-Modal LearningCode0
Contrastive Learning for Object DetectionCode0
Contrastive Learning for OOD in Object detectionCode0
Show:102550
← PrevPage 31 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