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 46514700 of 5044 papers

TitleStatusHype
SS-BRPE: Self-Supervised Blind Room Parameter Estimation Using Attention MechanismsCode0
Dense Depth Estimation in Monocular Endoscopy with Self-supervised Learning MethodsCode0
CellCLAT: Preserving Topology and Trimming Redundancy in Self-Supervised Cellular Contrastive LearningCode0
Self-Supervised Learning for Detecting AI-Generated Faces as AnomaliesCode0
Manifold Contrastive Learning with Variational Lie Group OperatorsCode0
Manifold Characteristics That Predict Downstream Task PerformanceCode0
Malafide: a novel adversarial convolutive noise attack against deepfake and spoofing detection systemsCode0
Zorro: the masked multimodal transformerCode0
Towards Scalable Foundation Models for Digital DermatologyCode0
Towards Self-Supervised Learning of Global and Object-Centric RepresentationsCode0
Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation LearningCode0
Magnitude-Phase Dual-Path Speech Enhancement Network based on Self-Supervised Embedding and Perceptual Contrast Stretch BoostingCode0
Self-Supervised Learning For Few-Shot Image ClassificationCode0
MAGMA: Manifold Regularization for MAEsCode0
Lung Nodule-SSM: Self-Supervised Lung Nodule Detection and Classification in Thoracic CT ImagesCode0
DoRA: Domain-Based Self-Supervised Learning Framework for Low-Resource Real Estate AppraisalCode0
Do Neural Scaling Laws Exist on Graph Self-Supervised Learning?Code0
Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR ModelsCode0
DomCLP: Domain-wise Contrastive Learning with Prototype Mixup for Unsupervised Domain GeneralizationCode0
Domain and Task-Focused Example Selection for Data-Efficient Contrastive Medical Image SegmentationCode0
Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?Code0
Low-Rank Approximation of Structural Redundancy for Self-Supervised LearningCode0
Does resistance to style-transfer equal Global Shape Bias? Measuring network sensitivity to global shape configurationCode0
CCRL: Contrastive Cell Representation LearningCode0
Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human ParsingCode0
SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised LearningCode0
Capsule Network Projectors are Equivariant and Invariant LearnersCode0
AAG: Self-Supervised Representation Learning by Auxiliary Augmentation with GNT-Xent LossCode0
Does Double Descent Occur in Self-Supervised Learning?Code0
Divergence-aware Federated Self-Supervised LearningCode0
SKID: Self-Supervised Learning for Knee Injury Diagnosis from MRI DataCode0
Looking Beyond Corners: Contrastive Learning of Visual Representations for Keypoint Detection and Description ExtractionCode0
A Dual-branch Self-supervised Representation Learning Framework for Tumour Segmentation in Whole Slide ImagesCode0
Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked PretrainingCode0
VIS-MAE: An Efficient Self-supervised Learning Approach on Medical Image Segmentation and ClassificationCode0
Can We Break Free from Strong Data Augmentations in Self-Supervised Learning?Code0
Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data CurriculumCode0
Local Masking Meets Progressive Freezing: Crafting Efficient Vision Transformers for Self-Supervised LearningCode0
Patch-Wise Self-Supervised Visual Representation Learning: A Fine-Grained ApproachCode0
Liver Fibrosis and NAS scoring from CT images using self-supervised learning and texture encodingCode0
LiPCoT: Linear Predictive Coding based Tokenizer for Self-supervised Learning of Time Series Data via Language ModelsCode0
A3: Active Adversarial Alignment for Source-Free Domain AdaptationCode0
SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised LearningCode0
Distribution Matching for Self-Supervised Transfer LearningCode0
Automatic separation of laminar-turbulent flows on aircraft wings and stabilisers via adaptive attention butterfly networkCode0
A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware CapabilityCode0
Self-supervised Learning for Panoptic Segmentation of Multiple Fruit Flower SpeciesCode0
Analyzing Data-Centric Properties for Graph Contrastive LearningCode0
Can Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions?Code0
ssVERDICT: Self-Supervised VERDICT-MRI for Enhanced Prostate Tumour CharacterisationCode0
Show:102550
← PrevPage 94 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