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 1351–1400 of 5044 papers

TitleStatusHype
Learning High-Level Policies for Model Predictive ControlCode1
Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous GraphsCode1
Learning Semantics-enriched Representation via Self-discovery, Self-classification, and Self-restorationCode1
Whitening for Self-Supervised Representation LearningCode1
Data-Efficient Reinforcement Learning with Self-Predictive RepresentationsCode1
TERA: Self-Supervised Learning of Transformer Encoder Representation for SpeechCode1
Self domain adapted networkCode1
Divide-and-Rule: Self-Supervised Learning for Survival Analysis in Colorectal CancerCode1
FLUID: A Unified Evaluation Framework for Flexible Sequential DataCode1
ADD: Analytically Differentiable Dynamics for Multi-Body Systems with Frictional ContactCode1
SACNN: Self-Attention Convolutional Neural Network for Low-Dose CT Denoising With Self-Supervised Perceptual Loss NetworkCode1
Subject-Aware Contrastive Learning for BiosignalsCode1
Patch SVDD: Patch-level SVDD for Anomaly Detection and SegmentationCode1
Space-Time Correspondence as a Contrastive Random WalkCode1
Gaining Insight into SARS-CoV-2 Infection and COVID-19 Severity Using Self-supervised Edge Features and Graph Neural NetworksCode1
The color out of space: learning self-supervised representations for Earth Observation imageryCode1
Self-Supervised Prototypical Transfer Learning for Few-Shot ClassificationCode1
Contrastive learning of global and local features for medical image segmentation with limited annotationsCode1
Self-supervised Learning on Graphs: Deep Insights and New DirectionCode1
Visual ChiralityCode1
Robot Perception enables Complex Navigation Behavior via Self-Supervised LearningCode1
When Does Self-Supervision Help Graph Convolutional Networks?Code1
ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic SegmentationCode1
Adversarial Self-Supervised Contrastive LearningCode1
Bootstrap your own latent: A new approach to self-supervised LearningCode1
Contrastive Multi-View Representation Learning on GraphsCode1
Self-Supervised Relational Reasoning for Representation LearningCode1
Self-supervised Learning from a Multi-view PerspectiveCode1
Few-Shot Generative Conversational Query RewritingCode1
Speaker Diarization as a Fully Online Learning Problem in MiniVoxCode1
Object Segmentation Without Labels with Large-Scale Generative ModelsCode1
3D Self-Supervised Methods for Medical ImagingCode1
Auto-Rectify Network for Unsupervised Indoor Depth EstimationCode1
Self-supervised Training of Graph Convolutional NetworksCode1
Self2Self With Dropout: Learning Self-Supervised Denoising From Single ImageCode1
Graph-based, Self-Supervised Program Repair from Diagnostic FeedbackCode1
Sketch-BERT: Learning Sketch Bidirectional Encoder Representation from Transformers by Self-supervised Learning of Sketch GestaltCode1
Self-Supervised Human Depth Estimation from Monocular VideosCode1
Enhancing Intrinsic Adversarial Robustness via Feature Pyramid DecoderCode1
Contrastive Self-Supervised Learning for Commonsense ReasoningCode1
Efficient and Information-Preserving Future Frame Prediction and BeyondCode1
Audio-Visual Instance Discrimination with Cross-Modal AgreementCode1
Extending and Analyzing Self-Supervised Learning Across DomainsCode1
Self6D: Self-Supervised Monocular 6D Object Pose EstimationCode1
Models GenesisCode1
Self-Supervised Monocular Scene Flow EstimationCode1
Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo MatchingCode1
Towards Better Generalization: Joint Depth-Pose Learning without PoseNetCode1
COVID-CT-Dataset: A CT Scan Dataset about COVID-19Code1
Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow EstimationCode1
Show:102550
← PrevPage 28 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