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 1151–1200 of 5044 papers

TitleStatusHype
SeiT++: Masked Token Modeling Improves Storage-efficient TrainingCode1
Deep Self-Supervised Representation Learning for Free-Hand SketchCode1
Boosting Contrastive Self-Supervised Learning with False Negative CancellationCode1
Adaptive Soft Contrastive LearningCode1
Anomaly Detection Requires Better RepresentationsCode1
EchoFM: Foundation Model for Generalizable Echocardiogram AnalysisCode1
Discriminative and Consistent Representation DistillationCode1
Invisible Backdoor Attack against Self-supervised LearningCode1
Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly DetectionCode1
Is Pseudo-Lidar needed for Monocular 3D Object detection?Code1
Echo-SyncNet: Self-supervised Cardiac View Synchronization in EchocardiographyCode1
Jointly Fine-Tuning “BERT-like” Self Supervised Models to Improve Multimodal Speech Emotion RecognitionCode1
Fragment-based Pretraining and Finetuning on Molecular GraphsCode1
Dive into Self-Supervised Learning for Medical Image Analysis: Data, Models and TasksCode1
Boosting Generalization in Bio-Signal Classification by Learning the Phase-Amplitude CouplingCode1
KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view StereoCode1
Fine-Tuning Self-Supervised Learning Models for End-to-End Pronunciation ScoringCode1
KOVIS: Keypoint-based Visual Servoing with Zero-Shot Sim-to-Real Transfer for Robotics ManipulationCode1
Divide-and-Rule: Self-Supervised Learning for Survival Analysis in Colorectal CancerCode1
DEER: Descriptive Knowledge Graph for Explaining Entity RelationshipsCode1
Fine-tune the pretrained ATST model for sound event detectionCode1
Boosting Self-Supervised Embeddings for Speech EnhancementCode1
Label Contrastive Coding based Graph Neural Network for Graph ClassificationCode1
Label-Efficient Learning in Agriculture: A Comprehensive ReviewCode1
DOBF: A Deobfuscation Pre-Training Objective for Programming LanguagesCode1
Efficiency for Free: Ideal Data Are Transportable RepresentationsCode1
DocMAE: Document Image Rectification via Self-supervised Representation LearningCode1
Large Pre-trained time series models for cross-domain Time series analysis tasksCode1
Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?Code1
A Note on Connecting Barlow Twins with Negative-Sample-Free Contrastive LearningCode1
Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability PerspectiveCode1
CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent MaskingCode1
FireRisk: A Remote Sensing Dataset for Fire Risk Assessment with Benchmarks Using Supervised and Self-supervised LearningCode1
Efficient and Information-Preserving Future Frame Prediction and BeyondCode1
Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in DrawingsCode1
A clinically motivated self-supervised approach for content-based image retrieval of CT liver imagesCode1
Finding Tori: Self-supervised Learning for Analyzing Korean Folk SongCode1
Learning Anatomically Consistent Embedding for Chest RadiographyCode1
Bootstrapping Autonomous Driving Radars with Self-Supervised LearningCode1
Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow EstimationCode1
Do Your Best and Get Enough Rest for Continual LearningCode1
Domain Knowledge-Informed Self-Supervised Representations for Workout Form AssessmentCode1
Learning Dense Object Descriptors from Multiple Views for Low-shot Category GeneralizationCode1
Learning Dynamic Belief Graphs to Generalize on Text-Based GamesCode1
Learning from partially labeled data for multi-organ and tumor segmentationCode1
Learning General Representation of 12-Lead Electrocardiogram with a Joint-Embedding Predictive ArchitectureCode1
Bootstrap your own latent: A new approach to self-supervised LearningCode1
Learning Graph Quantized TokenizersCode1
Bootstrap Your Own Latent - A New Approach to Self-Supervised LearningCode1
Fine-Grained Self-Supervised Learning with Jigsaw Puzzles for Medical Image ClassificationCode1
Show:102550
← PrevPage 24 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