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 1101–1150 of 5044 papers

TitleStatusHype
Multimodal Emotion Recognition with Transformer-Based Self Supervised Feature FusionCode1
Bidirectional Learning for Domain Adaptation of Semantic SegmentationCode1
Multimodal Fusion and Vision-Language Models: A Survey for Robot VisionCode1
MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion RecognitionCode1
Systematic comparison of semi-supervised and self-supervised learning for medical image classificationCode1
DRL-Based Federated Self-Supervised Learning for Task Offloading and Resource Allocation in ISAC-Enabled Vehicle Edge ComputingCode1
DiffPMAE: Diffusion Masked Autoencoders for Point Cloud ReconstructionCode1
DiffSim: Taming Diffusion Models for Evaluating Visual SimilarityCode1
Empowering Collaborative Filtering with Principled Adversarial Contrastive LossCode1
Diffusion Auto-regressive Transformer for Effective Self-supervised Time Series ForecastingCode1
Multimodal Clustering Networks for Self-supervised Learning from Unlabeled VideosCode1
Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised LearningCode1
Do Your Best and Get Enough Rest for Continual LearningCode1
Harnessing small projectors and multiple views for efficient vision pretrainingCode1
An Investigation into Whitening Loss for Self-supervised LearningCode1
Digging Into Self-Supervised Monocular Depth EstimationCode1
Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular DomainsCode1
Digging into Uncertainty in Self-supervised Multi-view StereoCode1
eProduct: A Million-Scale Visual Search Benchmark to Address Product Recognition ChallengesCode1
Exchange means change: an unsupervised single-temporal change detection framework based on intra- and inter-image patch exchangeCode1
BIOSCAN-5M: A Multimodal Dataset for Insect BiodiversityCode1
Enhanced Masked Image Modeling to Avoid Model Collapse on Multi-modal MRI DatasetsCode1
Enhancing Intrinsic Adversarial Robustness via Feature Pyramid DecoderCode1
Extending global-local view alignment for self-supervised learning with remote sensing imageryCode1
Enhancing Network Initialization for Medical AI Models Using Large-Scale, Unlabeled Natural ImagesCode1
DINOv2 based Self Supervised Learning For Few Shot Medical Image SegmentationCode1
Benchmarking Self-Supervised Learning on Diverse Pathology DatasetsCode1
DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image AnalysisCode1
Multi-behavior Self-supervised Learning for RecommendationCode1
DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive LearningCode1
Equivariant Contrastive LearningCode1
Deep Self-Supervised Representation Learning for Free-Hand SketchCode1
Adaptive Soft Contrastive LearningCode1
ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic SegmentationCode1
A Discrepancy Aware Framework for Robust Anomaly DetectionCode1
Evaluating Self-Supervised Learning for Molecular Graph EmbeddingsCode1
DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose EstimationCode1
Evaluation of Speech Representations for MOS predictionCode1
Offline Visual Representation Learning for Embodied NavigationCode1
SelfAugment: Automatic Augmentation Policies for Self-Supervised LearningCode1
DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech ModelsCode1
Dissecting Image CropsCode1
Dissecting Self-Supervised Learning Methods for Surgical Computer VisionCode1
Distance-wise Prototypical Graph Neural Network in Node Imbalance ClassificationCode1
Distilling Knowledge from Self-Supervised Teacher by Embedding Graph AlignmentCode1
Adopting Self-Supervised Learning into Unsupervised Video Summarization through Restorative ScoreCode1
Anomaly Detection in Video via Self-Supervised and Multi-Task LearningCode1
Distilling Visual Priors from Self-Supervised LearningCode1
Every Node is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph ClusteringCode1
Self-supervised Pseudo Multi-class Pre-training for Unsupervised Anomaly Detection and Segmentation in Medical ImagesCode1
Show:102550
← PrevPage 23 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