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 3651–3700 of 5044 papers

TitleStatusHype
That Sounds Right: Auditory Self-Supervision for Dynamic Robot ManipulationCode0
Pixel-global Self-supervised Learning with Uncertainty-aware Context Stabilizer—0
What shapes the loss landscape of self-supervised learning?—0
Ten Years after ImageNet: A 360° Perspective on AI—0
Slimmable Networks for Contrastive Self-supervised LearningCode0
Match to Win: Analysing Sequences Lengths for Efficient Self-supervised Learning in Speech and Audio—0
Minimalistic Unsupervised Learning with the Sparse Manifold Transform—0
Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis—0
Joint Embedding Self-Supervised Learning in the Kernel Regime—0
Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations—0
Graph Soft-Contrastive Learning via Neighborhood Ranking—0
Masked Multi-Step Multivariate Time Series Forecasting with Future Information—0
Efficient Medical Image Assessment via Self-supervised Learning—0
Non-contrastive representation learning for intervals from well logs—0
Audio Barlow Twins: Self-Supervised Audio Representation LearningCode0
3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion—0
End-to-End Lyrics Recognition with Self-supervised Learning—0
Improving Image Clustering through Sample Ranking and Its Application to remote--sensing imagesCode0
Deep Attentive Belief Propagation: Integrating Reasoning and Learning for Solving Constraint Optimization Problems—0
Self-supervised Learning for Unintentional Action Prediction—0
Controllable Face Manipulation and UV Map Generation by Self-supervised Learning—0
Self-supervised Learning for Clustering of Wireless Spectrum ActivityCode0
Cross-domain Voice Activity Detection with Self-Supervised Representations—0
Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement LearningCode0
WeLM: A Well-Read Pre-trained Language Model for Chinese—0
Locally Constrained Representations in Reinforcement Learning—0
The Geometry of Self-supervised Learning Models and its Impact on Transfer Learning—0
On PAC Learning Halfspaces in Non-interactive Local Privacy Model with Public Unlabeled Data—0
Self-supervised learning of hologram reconstruction using physics consistency—0
Few-Shot Classification with Contrastive Learning—0
Enhance the Visual Representation via Discrete Adversarial TrainingCode0
Modeling Multiple Views via Implicitly Preserving Global Consistency and Local ComplementarityCode0
Exploring StyleGAN Latent Space for Face Alignment with Limited Training Data—0
Graph Contrastive Learning with Cross-view Reconstruction—0
LAVIS: A Library for Language-Vision Intelligence—0
Self-Relation Attention and Temporal Awareness for Emotion Recognition via Vocal BurstCode0
SeRP: Self-Supervised Representation Learning Using Perturbed Point Clouds—0
Just Noticeable Difference Modeling for Face Recognition System—0
Graph Neural Networks for Molecules—0
OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning—0
Self-supervised Learning for Panoptic Segmentation of Multiple Fruit Flower SpeciesCode0
Self-supervised Learning for Heterogeneous Graph via Structure Information based on Metapath—0
SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised LearningCode0
MimCo: Masked Image Modeling Pre-training with Contrastive Teacher—0
Self-supervised multimodal neuroimaging yields predictive representations for a spectrum of Alzheimer's phenotypesCode0
Improving Self-supervised Learning for Out-of-distribution Task via Auxiliary ClassifierCode0
Real-Time Cattle Interaction Recognition via Triple-stream Network—0
Robust and Efficient Imbalanced Positive-Unlabeled Learning with Self-supervisionCode0
Imaging with Equivariant Deep Learning—0
Federated Transfer Learning with Multimodal Data—0
Show:102550
← PrevPage 74 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