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 851–900 of 5044 papers

TitleStatusHype
Dual Path Learning for Domain Adaptation of Semantic SegmentationCode1
Contrastive Graph Learning for Population-based fMRI ClassificationCode1
Dual-distribution discrepancy with self-supervised refinement for anomaly detection in medical imagesCode1
Attentive Symmetric Autoencoder for Brain MRI SegmentationCode1
Big Self-Supervised Models Advance Medical Image ClassificationCode1
Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot LearningCode1
Audio-Adaptive Activity Recognition Across Video DomainsCode1
Dual Intents Graph Modeling for User-centric Group DiscoveryCode1
Contrastive Learning Inverts the Data Generating ProcessCode1
Active Learning Through a Covering LensCode1
Contrastive Learning Is Spectral Clustering On Similarity GraphCode1
Multi-Source Contrastive Learning from Musical AudioCode1
Systematic comparison of semi-supervised and self-supervised learning for medical image classificationCode1
Object Segmentation Without Labels with Large-Scale Generative ModelsCode1
CR-GAN: Learning Complete Representations for Multi-view GenerationCode1
DualNet: Continual Learning, Fast and SlowCode1
Music Classification: Beyond Supervised Learning, Towards Real-world ApplicationsCode1
Contrastive Learning with Boosted MemorizationCode1
Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity RecognitionCode1
MVP: Unified Motion and Visual Self-Supervised Learning for Large-Scale Robotic NavigationCode1
Audio-Visual Instance Discrimination with Cross-Modal AgreementCode1
Contrastive Learning with Stronger AugmentationsCode1
Contrastive Learning with Synthetic PositivesCode1
Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy ImagesCode1
Contrastive Multi-View Representation Learning on GraphsCode1
Contrastive Neural Processes for Self-Supervised LearningCode1
Bidirectional Learning for Domain Adaptation of Semantic SegmentationCode1
Neural Manifold Clustering and EmbeddingCode1
AASAE: Augmentation-Augmented Stochastic AutoencodersCode1
Contrastive Representation Learning for Gaze EstimationCode1
Deep Unfolded Tensor Robust PCA with Self-supervised LearningCode1
Neutral Face Game Character Auto-Creation via PokerFace-GANCode1
Contrastive Self-Supervised Learning for Commonsense ReasoningCode1
M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA frameworkCode1
Augmentation-Free Self-Supervised Learning on GraphsCode1
Non-Contrastive Self-Supervised Learning of Utterance-Level Speech RepresentationsCode1
Do Your Best and Get Enough Rest for Continual LearningCode1
NTopo: Mesh-free Topology Optimization using Implicit Neural RepresentationsCode1
NVS-SQA: Exploring Self-Supervised Quality Representation Learning for Neurally Synthesized Scenes without ReferencesCode1
Object-aware Contrastive Learning for Debiased Scene RepresentationCode1
Contrastive Self-supervised Sequential Recommendation with Robust AugmentationCode1
ATD: Augmenting CP Tensor Decomposition by Self SupervisionCode1
Self-supervised Spatial Reasoning on Multi-View Line DrawingsCode1
Contrastive Transformation for Self-supervised Correspondence LearningCode1
Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement LearningCode1
ControlEdit: A MultiModal Local Clothing Image Editing MethodCode1
DeLoRes: Decorrelating Latent Spaces for Low-Resource Audio Representation LearningCode1
An Embarrassingly Simple Backdoor Attack on Self-supervised LearningCode1
AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language ProcessingCode1
DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech ModelsCode1
Show:102550
← PrevPage 18 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