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 4301–4350 of 5044 papers

TitleStatusHype
Multi-Token Enhancing for Vision Representation Learning—0
Multi-view Contrastive Self-Supervised Learning of Accounting Data Representations for Downstream Audit Tasks—0
Multi-view Feature Extraction based on Dual Contrastive Head—0
Multi-view Feature Extraction based on Triple Contrastive Heads—0
Multi-View Subgraph Neural Networks: Self-Supervised Learning with Scarce Labeled Data—0
MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts—0
MUSE: Multi-View Contrastive Learning for Heterophilic Graphs—0
MusiCoder: A Universal Music-Acoustic Encoder Based on Transformers—0
Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders—0
MV2MAE: Multi-View Video Masked Autoencoders—0
MVCNet: Multiview Contrastive Network for Unsupervised Representation Learning for 3D CT Lesions—0
Navigating the Future of Federated Recommendation Systems with Foundation Models—0
Near, far: Patch-ordering enhances vision foundation models' scene understanding—0
Negative Selection by Clustering for Contrastive Learning in Human Activity Recognition—0
NeRFEditor: Differentiable Style Decomposition for Full 3D Scene Editing—0
NERULA: A Dual-Pathway Self-Supervised Learning Framework for Electrocardiogram Signal Analysis—0
NEST-RQ: Next Token Prediction for Speech Self-Supervised Pre-Training—0
NetFlowGen: Leveraging Generative Pre-training for Network Traffic Dynamics—0
Neural Algorithmic Reasoners are Implicit Planners—0
Neural Inverse Rendering of an Indoor Scene from a Single Image—0
Neural Modes: Self-supervised Learning of Nonlinear Modal Subspaces—0
Neural spatio-temporal reasoning with object-centric self-supervised learning—0
NeuroMoCo: A Neuromorphic Momentum Contrast Learning Method for Spiking Neural Networks—0
Neurosymbolic AI - Why, What, and How—0
New Test-Time Scenario for Biosignal: Concept and Its Approach—0
NICT Kyoto Submission for the WMT’20 Quality Estimation Task: Intermediate Training for Domain and Task Adaptation—0
Noise2Filter: fast, self-supervised learning and real-time reconstruction for 3D Computed Tomography—0
Noise-Robust Target-Speaker Voice Activity Detection Through Self-Supervised Pretraining—0
Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters—0
Noisy Adversarial Training—0
Noisy Node Classification by Bi-level Optimization based Multi-teacher Distillation—0
Non-Cartesian Self-Supervised Physics-Driven Deep Learning Reconstruction for Highly-Accelerated Multi-Echo Spiral fMRI—0
Non-Causal to Causal SSL-Supported Transfer Learning: Towards a High-Performance Low-Latency Speech Vocoder—0
Non-contrastive representation learning for intervals from well logs—0
Non-Contrastive Learning-based Behavioural Biometrics for Smart IoT Devices—0
Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech—0
Nonequilibrium thermodynamics of self-supervised learning—0
Non-intrusive Load Monitoring based on Self-supervised Learning—0
Nonlinear Equivariant Imaging: Learning Multi-Parametric Tissue Mapping without Ground Truth for Compressive Quantitative MRI—0
Non-Parametric Representation Learning with Kernels—0
Non-Rigid Image Registration Using Self-Supervised Fully Convolutional Networks without Training Data—0
Non-transferable Pruning—0
Non-Uniform Exposure Imaging via Neuromorphic Shutter Control—0
Normalizing self-supervised learning for provably reliable Change Point Detection—0
Noro: A Noise-Robust One-shot Voice Conversion System with Hidden Speaker Representation Capabilities—0
No Shifted Augmentations (NSA): strong baselines for self-supervised Anomaly Detection—0
Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting—0
Novelty Detection via Contrastive Learning with Negative Data Augmentation—0
Novel View Synthesis with View-Dependent Effects from a Single Image—0
NTKCPL: Active Learning on Top of Self-Supervised Model by Estimating True Coverage—0
Show:102550
← PrevPage 87 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