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 16011650 of 5044 papers

TitleStatusHype
Privacy-Preserving Models for Legal Natural Language ProcessingCode0
A Hierarchical Regression Chain Framework for Affective Vocal Burst RecognitionCode0
Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised LearningCode0
For self-supervised learning, Rationality implies generalization, provablyCode0
Consistency is the key to further mitigating catastrophic forgetting in continual learningCode0
ActBERT: Learning Global-Local Video-Text RepresentationsCode0
Forensic Histopathological Recognition via a Context-Aware MIL Network Powered by Self-Supervised Contrastive LearningCode0
Pretraining ECG Data with Adversarial Masking Improves Model Generalizability for Data-Scarce TasksCode0
Preserving Modality Structure Improves Multi-Modal LearningCode0
Focus on the Positives: Self-Supervised Learning for Biodiversity MonitoringCode0
Predicting within and across language phoneme recognition performance of self-supervised learning speech pre-trained modelsCode0
Pretext Tasks selection for multitask self-supervised speech representation learningCode0
FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive ModelsCode0
Frequency-Guided Masking for Enhanced Vision Self-Supervised LearningCode0
ConMAE: Contour Guided MAE for Unsupervised Vehicle Re-IdentificationCode0
PRETI: Patient-Aware Retinal Foundation Model via Metadata-Guided Representation LearningCode0
Fitting a Directional Microstructure Model to Diffusion-Relaxation MRI Data with Self-Supervised Machine LearningCode0
Precision at Scale: Domain-Specific Datasets On-DemandCode0
Conformal Credal Self-Supervised LearningCode0
POWN: Prototypical Open-World Node ClassificationCode0
Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative StudyCode0
Confidence-aware Adversarial Learning for Self-supervised Semantic MatchingCode0
Predicting Stroke through Retinal Graphs and Multimodal Self-supervised LearningCode0
Conditional independence for pretext task selection in Self-supervised speech representation learningCode0
Fine-grained Hand Gesture Recognition in Multi-viewpoint Hand HygieneCode0
PRSNet: A Masked Self-Supervised Learning Pedestrian Re-Identification MethodCode0
Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark DiscoveryCode0
Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio MaskingCode0
Positive and negative sampling strategies for self-supervised learning on audio-video dataCode0
Context-Aware Predictive Coding: A Representation Learning Framework for WiFi SensingCode0
Plasticity-Optimized Complementary Networks for Unsupervised Continual LearningCode0
Few-Max: Few-Shot Domain Adaptation for Unsupervised Contrastive Representation LearningCode0
PixMIM: Rethinking Pixel Reconstruction in Masked Image ModelingCode0
PixT3: Pixel-based Table-To-Text GenerationCode0
FedRSU: Federated Learning for Scene Flow Estimation on Roadside UnitsCode0
Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud Semantic SegmentationCode0
Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data HeterogeneityCode0
FusDom: Combining In-Domain and Out-of-Domain Knowledge for Continuous Self-Supervised LearningCode0
Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech TransformersCode0
PECoP: Parameter Efficient Continual Pretraining for Action Quality AssessmentCode0
PEFT for Speech: Unveiling Optimal Placement, Merging Strategies, and Ensemble TechniquesCode0
PFML: Self-Supervised Learning of Time-Series Data Without Representation CollapseCode0
PatchRot: A Self-Supervised Technique for Training Vision TransformersCode0
Compound Figure Separation of Biomedical Images: Mining Large Datasets for Self-supervised LearningCode0
Compound Figure Separation of Biomedical Images with Side LossCode0
PARTICLE: Part Discovery and Contrastive Learning for Fine-grained RecognitionCode0
Optimizing the Noise in Self-Supervised Learning: from Importance Sampling to Noise-Contrastive EstimationCode0
NeuroMixGDP: A Neural Collapse-Inspired Random Mixup for Private Data ReleaseCode0
Optimizing Likelihood-free Inference using Self-supervised Neural Symmetry EmbeddingsCode0
Optimizing Speech Multi-View Feature Fusion through Conditional ComputationCode0
Show:102550
← PrevPage 33 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