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 501–550 of 5044 papers

TitleStatusHype
Self-Supervised Learning for Endoscopic Video AnalysisCode1
Time Does Tell: Self-Supervised Time-Tuning of Dense Image RepresentationsCode1
Exploring Unsupervised Cell Recognition with Prior Self-activation MapsCode1
Efficient Representation Learning for Healthcare with Cross-Architectural Self-SupervisionCode1
Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based SimilarityCode1
Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud VideosCode1
MUSE: Music Recommender System with Shuffle Play Recommendation EnhancementCode1
GiGaMAE: Generalizable Graph Masked Autoencoder via Collaborative Latent Space ReconstructionCode1
A Survey on Deep Multi-modal Learning for Body Language Recognition and GenerationCode1
Half-Hop: A graph upsampling approach for slowing down message passingCode1
LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series ForecastersCode1
Enhancing Network Initialization for Medical AI Models Using Large-Scale, Unlabeled Natural ImagesCode1
Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical ImagingCode1
Generalizing Event-Based Motion Deblurring in Real-World ScenariosCode1
Fine-Grained Self-Supervised Learning with Jigsaw Puzzles for Medical Image ClassificationCode1
Dual Intents Graph Modeling for User-centric Group DiscoveryCode1
Prompted Contrast with Masked Motion Modeling: Towards Versatile 3D Action Representation LearningCode1
Improving Medical Image Classification in Noisy Labels Using Only Self-supervised PretrainingCode1
SSL-SoilNet: A Hybrid Transformer-based Framework with Self-Supervised Learning for Large-scale Soil Organic Carbon PredictionCode1
Scaling may be all you need for achieving human-level object recognition capacity with human-like visual experienceCode1
Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly DetectionCode1
A Symbolic Character-Aware Model for Solving Geometry ProblemsCode1
Finding Tori: Self-supervised Learning for Analyzing Korean Folk SongCode1
VG-SSL: Benchmarking Self-supervised Representation Learning Approaches for Visual Geo-localizationCode1
CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent MaskingCode1
Stochastic positional embeddings improve masked image modelingCode1
Gloss-free Sign Language Translation: Improving from Visual-Language PretrainingCode1
vox2vec: A Framework for Self-supervised Contrastive Learning of Voxel-level Representations in Medical ImagesCode1
SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image SegmentationCode1
Learning Navigational Visual Representations with Semantic Map SupervisionCode1
Downstream-agnostic Adversarial ExamplesCode1
Zero-note samba: Self-supervised beat trackingCode1
Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop FeedbackCode1
Self2Self+: Single-Image Denoising with Self-Supervised Learning and Image Quality Assessment LossCode1
The Role of Entropy and Reconstruction in Multi-View Self-Supervised LearningCode1
MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook AssignmentsCode1
Systematic comparison of semi-supervised and self-supervised learning for medical image classificationCode1
L-DAWA: Layer-wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation LearningCode1
FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object SegmentationCode1
Mini-Batch Optimization of Contrastive LossCode1
Self-Supervised Learning with Lie Symmetries for Partial Differential EquationsCode1
Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised LearningCode1
Unsupervised 3D registration through optimization-guided cyclical self-trainingCode1
DUET: 2D Structured and Approximately Equivariant RepresentationsCode1
Unsupervised Episode Generation for Graph Meta-learningCode1
Structuring Representation Geometry with Rotationally Equivariant Contrastive LearningCode1
How to Efficiently Adapt Large Segmentation Model(SAM) to Medical ImagesCode1
Inter-Instance Similarity Modeling for Contrastive LearningCode1
A Reference-less Quality Metric for Automatic Speech Recognition via Contrastive-Learning of a Multi-Language Model with Self-SupervisionCode1
Spatial-Temporal Graph Learning with Adversarial Contrastive AdaptationCode1
Show:102550
← PrevPage 11 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