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 1901–1950 of 5044 papers

TitleStatusHype
PESTO: Pitch Estimation with Self-supervised Transposition-equivariant Objective—0
Probabilistic Self-supervised Learning via Scoring Rules Minimization—0
Robust Recommender System: A Survey and Future DirectionsCode0
Prototype-based Dataset ComparisonCode1
Inferring Actual Treatment Pathways from Patient RecordsCode0
A Survey of the Impact of Self-Supervised Pretraining for Diagnostic Tasks with Radiological Images—0
GenSelfDiff-HIS: Generative Self-Supervision Using Diffusion for Histopathological Image SegmentationCode1
Acoustic-to-articulatory inversion for dysarthric speech: Are pre-trained self-supervised representations favorable?—0
COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using TransformersCode1
DoRA: Domain-Based Self-Supervised Learning Framework for Low-Resource Real Estate AppraisalCode0
Self-Supervised Video Transformers for Isolated Sign Language Recognition—0
Remixing-based Unsupervised Source Separation from Scratch—0
Geometry-aware Line Graph Transformer Pre-training for Molecular Property Prediction—0
Blind Source Separation of Single-Channel Mixtures via Multi-Encoder AutoencodersCode1
Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data—0
Companion Animal Disease Diagnostics based on Literal-aware Medical Knowledge Graph Representation LearningCode0
RAMP: Retrieval-Augmented MOS Prediction via Confidence-based Dynamic Weighting—0
Emergence of Segmentation with Minimalistic White-Box TransformersCode3
Towards quantitative precision for ECG analysis: Leveraging state space models, self-supervision and patient metadataCode1
Detect, Augment, Compose, and Adapt: Four Steps for Unsupervised Domain Adaptation in Object DetectionCode1
Unsupervised Active Learning: Optimizing Labeling Cost-Effectiveness for Automatic Speech Recognition—0
Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads—0
Self-Supervision for Tackling Unsupervised Anomaly Detection: Pitfalls and Opportunities—0
MS-Net: A Multi-modal Self-supervised Network for Fine-Grained Classification of Aircraft in SAR Images—0
Unleash Model Potential: Bootstrapped Meta Self-supervised Learning—0
End-to-End Driving via Self-Supervised Imitation Learning Using Camera and LiDAR Data—0
Forensic Histopathological Recognition via a Context-Aware MIL Network Powered by Self-Supervised Contrastive LearningCode0
Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class DiscoveryCode0
AtmoRep: A stochastic model of atmosphere dynamics using large scale representation learning—0
Self-supervised learning for hotspot detection and isolation from thermal images—0
Preserving Modality Structure Improves Multi-Modal LearningCode0
Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objects—0
REB: Reducing Biases in Representation for Industrial Anomaly DetectionCode1
Head-Tail Cooperative Learning Network for Unbiased Scene Graph GenerationCode0
MOFO: MOtion FOcused Self-Supervision for Video UnderstandingCode0
Self-Supervised Learning for Endoscopic Video AnalysisCode1
Time Does Tell: Self-Supervised Time-Tuning of Dense Image RepresentationsCode1
An Effective Transformer-based Contextual Model and Temporal Gate Pooling for Speaker IdentificationCode0
GOPro: Generate and Optimize Prompts in CLIP using Self-Supervised LearningCode0
Exploring Unsupervised Cell Recognition with Prior Self-activation MapsCode1
Masked Momentum Contrastive Learning for Zero-shot Semantic Understanding—0
Quantile-based Maximum Likelihood Training for Outlier DetectionCode0
Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection—0
Enhancing Transformers without Self-supervised Learning: A Loss Landscape Perspective in Sequential Recommendation—0
A Review on Objective-Driven Artificial Intelligence—0
Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked AutoencodersCode2
Learning Multiscale Consistency for Self-supervised Electron Microscopy Instance Segmentation—0
Efficient Representation Learning for Healthcare with Cross-Architectural Self-SupervisionCode1
Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based SimilarityCode1
MUSE: Music Recommender System with Shuffle Play Recommendation EnhancementCode1
Show:102550
← PrevPage 39 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