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 251–300 of 5044 papers

TitleStatusHype
Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity RecognitionCode1
DATA: Domain-Aware and Task-Aware Self-supervised LearningCode1
Data-Efficient Reinforcement Learning with Self-Predictive RepresentationsCode1
Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical ImagingCode1
Contrastive Learning with Boosted MemorizationCode1
Contrastive Learning with Stronger AugmentationsCode1
M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA frameworkCode1
AASAE: Augmentation-Augmented Stochastic AutoencodersCode1
Contrastive Learning with Synthetic PositivesCode1
Contrastive Learning Is Spectral Clustering On Similarity GraphCode1
Contrastive Learning Inverts the Data Generating ProcessCode1
Contrastive learning of global and local features for medical image segmentation with limited annotationsCode1
Contrastive Graph Learning for Population-based fMRI ClassificationCode1
Contrastive Hierarchical ClusteringCode1
Contrastive Learning of Musical RepresentationsCode1
Contrastive Multi-View Representation Learning on GraphsCode1
Active Learning Through a Covering LensCode1
Continual Learning, Fast and SlowCode1
A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action RecognitionCode1
Context Matters: Graph-based Self-supervised Representation Learning for Medical ImagesCode1
Contextually Affinitive Neighborhood Refinery for Deep ClusteringCode1
Continually Learning Self-Supervised Representations with Projected Functional RegularizationCode1
A Large Scale Event-based Detection Dataset for AutomotiveCode1
Container: Context Aggregation NetworksCode1
Consistent Explanations by Contrastive LearningCode1
A self-supervised learning strategy for postoperative brain cavity segmentation simulating resectionsCode1
Container: Context Aggregation NetworkCode1
Context-Aware Sequence Alignment using 4D Skeletal AugmentationCode1
Continual Self-supervised Learning: Towards Universal Multi-modal Medical Data Representation LearningCode1
Contrastive Neural Processes for Self-Supervised LearningCode1
ConCL: Concept Contrastive Learning for Dense Prediction Pre-training in Pathology ImagesCode1
Concept Generalization in Visual Representation LearningCode1
Conditional Deformable Image Registration with Convolutional Neural NetworkCode1
Comparing Self-Supervised Learning Techniques for Wearable Human Activity RecognitionCode1
A Hybrid Self-Supervised Learning Framework for Vertical Federated LearningCode1
Comprehensive Layer-wise Analysis of SSL Models for Audio Deepfake DetectionCode1
Confidence-based Visual Dispersal for Few-shot Unsupervised Domain AdaptationCode1
Combining Self-Training and Self-Supervised Learning for Unsupervised Disfluency DetectionCode1
Combating Representation Learning Disparity with Geometric HarmonizationCode1
COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using TransformersCode1
A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-IdentificationCode1
AgriCLIP: Adapting CLIP for Agriculture and Livestock via Domain-Specialized Cross-Model AlignmentCode1
Combating Bilateral Edge Noise for Robust Link PredictionCode1
Co-mining: Self-Supervised Learning for Sparsely Annotated Object DetectionCode1
CONSAC: Robust Multi-Model Fitting by Conditional Sample ConsensusCode1
A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural NetworksCode1
Benchmarking Pathology Feature Extractors for Whole Slide Image ClassificationCode1
CoCoNets: Continuous Contrastive 3D Scene RepresentationsCode1
COCOA: Cross Modality Contrastive Learning for Sensor DataCode1
3rd Place: A Global and Local Dual Retrieval Solution to Facebook AI Image Similarity ChallengeCode1
Show:102550
← PrevPage 6 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