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 451–500 of 5044 papers

TitleStatusHype
ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo SystemsCode1
Adversarial Self-Supervised Contrastive LearningCode1
AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking KeypointsCode1
Fragment-based Pretraining and Finetuning on Molecular GraphsCode1
Effective Self-supervised Pre-training on Low-compute Networks without DistillationCode1
Echo-SyncNet: Self-supervised Cardiac View Synchronization in EchocardiographyCode1
Automated segmentation of lesions and organs at risk on [68Ga]Ga-PSMA-11 PET/CT images using self-supervised learning with Swin UNETRCode1
Efficiency for Free: Ideal Data Are Transportable RepresentationsCode1
Automated Self-Supervised Learning for GraphsCode1
Automatically Discovering and Learning New Visual Categories with Ranking StatisticsCode1
Crowdsourced 3D Mapping: A Combined Multi-View Geometry and Self-Supervised Learning ApproachCode1
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual RepresentationsCode1
A Review on Self-Supervised Learning for Time Series Anomaly Detection: Recent Advances and Open ChallengesCode1
D2C: Diffusion-Denoising Models for Few-shot Conditional GenerationCode1
DABS: A Domain-Agnostic Benchmark for Self-Supervised LearningCode1
Automatic identification of segmentation errors for radiotherapy using geometric learningCode1
3D Object Detection with a Self-supervised Lidar Scene Flow BackboneCode1
Data-Centric Learning from Unlabeled Graphs with Diffusion ModelCode1
Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentationCode1
data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setupCode1
CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World DomainsCode1
AutoNovel: Automatically Discovering and Learning Novel Visual CategoriesCode1
Data-Efficient Reinforcement Learning with Self-Predictive RepresentationsCode1
Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the LeastCode1
Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical ImagingCode1
What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable InsightsCode1
AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech RepresentationCode1
Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill LearningCode1
2nd Place Solution to Facebook AI Image Similarity Challenge Matching TrackCode1
Adversarial Masking for Self-Supervised LearningCode1
A vector quantized masked autoencoder for speech emotion recognitionCode1
Decoupled Contrastive LearningCode1
Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural FieldsCode1
AVF-MAE++: Scaling Affective Video Facial Masked Autoencoders via Efficient Audio-Visual Self-Supervised LearningCode1
EchoFM: Foundation Model for Generalizable Echocardiogram AnalysisCode1
GestSync: Determining who is speaking without a talking headCode1
Adapting Self-Supervised Vision Transformers by Probing Attention-Conditioned Masking ConsistencyCode1
Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech RecognitionCode1
ECONET: Effective Continual Pretraining of Language Models for Event Temporal ReasoningCode1
Backdoor Attacks on Self-Supervised LearningCode1
Backdoor Defense via Decoupling the Training ProcessCode1
Deep Self-Supervised Representation Learning for Free-Hand SketchCode1
Deep Unfolded Tensor Robust PCA with Self-supervised LearningCode1
GMSS: Graph-Based Multi-Task Self-Supervised Learning for EEG Emotion RecognitionCode1
BYOL-S: Learning Self-supervised Speech Representations by BootstrappingCode1
BADGR: An Autonomous Self-Supervised Learning-Based Navigation SystemCode1
Bag of Instances Aggregation Boosts Self-supervised DistillationCode1
Anatomical Invariance Modeling and Semantic Alignment for Self-supervised Learning in 3D Medical Image AnalysisCode1
Anatomy-aware Self-supervised Learning for Anomaly Detection in Chest RadiographsCode1
BYOL for Audio: Self-Supervised Learning for General-Purpose Audio RepresentationCode1
Show:102550
← PrevPage 10 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