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

Showing 10011050 of 5044 papers

TitleStatusHype
DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose EstimationCode1
Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the WildCode1
Adaptive Graph Contrastive Learning for RecommendationCode1
LGSDF: Continual Global Learning of Signed Distance Fields Aided by Local UpdatingCode1
Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical ImagingCode1
Lexi: Self-Supervised Learning of the UI LanguageCode1
Deciphering and integrating invariants for neural operator learning with various physical mechanismsCode1
Light-weight probing of unsupervised representations for Reinforcement LearningCode1
Dissecting Self-Supervised Learning Methods for Surgical Computer VisionCode1
Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked AutoencodersCode1
Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial RobustnessCode1
MEA-Defender: A Robust Watermark against Model Extraction AttackCode1
Decoupled Contrastive LearningCode1
BARThez: a Skilled Pretrained French Sequence-to-Sequence ModelCode1
BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable BasisCode1
LISBET: a machine learning model for the automatic segmentation of social behavior motifsCode1
Learning with Unmasked Tokens Drives Stronger Vision LearnersCode1
Self-Supervised Learning by Estimating Twin Class DistributionsCode1
Mean-Shifted Contrastive Loss for Anomaly DetectionCode1
DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image AnalysisCode1
Animating Landscape: Self-Supervised Learning of Decoupled Motion and Appearance for Single-Image Video SynthesisCode1
Self-Supervised Learning for Anomalous Sound DetectionCode1
Domain Knowledge-Informed Self-Supervised Representations for Workout Form AssessmentCode1
DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive LearningCode1
Distance-wise Prototypical Graph Neural Network in Node Imbalance ClassificationCode1
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentationCode1
Mean Shift for Self-Supervised LearningCode1
MixCo: Mix-up Contrastive Learning for Visual RepresentationCode1
Digging Into Self-Supervised Monocular Depth EstimationCode1
SpeechPrompt: An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing TasksCode1
Masked Trajectory Models for Prediction, Representation, and ControlCode1
DiffUTE: Universal Text Editing Diffusion ModelCode1
3D-CSL: self-supervised 3D context similarity learning for Near-Duplicate Video RetrievalCode1
Digging into Uncertainty in Self-supervised Multi-view StereoCode1
Diffusion Auto-regressive Transformer for Effective Self-supervised Time Series ForecastingCode1
Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose EstimationCode1
Beyond [cls]: Exploring the true potential of Masked Image Modeling representationsCode1
ADD: Analytically Differentiable Dynamics for Multi-Body Systems with Frictional ContactCode1
Masked Surfel Prediction for Self-Supervised Point Cloud LearningCode1
BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving ScenariosCode1
DiffPMAE: Diffusion Masked Autoencoders for Point Cloud ReconstructionCode1
Physics Driven Deep Retinex Fusion for Adaptive Infrared and Visible Image FusionCode1
DiffBody: Diffusion-based Pose and Shape Editing of Human ImagesCode1
Extending global-local view alignment for self-supervised learning with remote sensing imageryCode1
Deep fiber clustering: Anatomically informed fiber clustering with self-supervised deep learning for fast and effective tractography parcellationCode1
An Empirical Study of Training Self-Supervised Vision TransformersCode1
Differentiable Raycasting for Self-supervised Occupancy ForecastingCode1
BENDR: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG dataCode1
BenchMD: A Benchmark for Unified Learning on Medical Images and SensorsCode1
DiffSim: Taming Diffusion Models for Evaluating Visual SimilarityCode1
Show:102550
← PrevPage 21 of 101Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Pretraining: NoneImages & Text57.5Unverified
2Pretraining: ShEDImages & Text54.3Unverified
3Pretraining: e-MixImages & Text48.9Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50Accuracy91.7Unverified
2ResNet18Accuracy91.02Unverified
3MV-MRAccuracy89.67Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy93.89Unverified
2ResNet18average top-1 classification accuracy92.58Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy72.51Unverified
2ResNet18average top-1 classification accuracy69.31Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet50)Top-1 Accuracy82.64Unverified
2CorInfomax (ResNet18)Top-1 Accuracy80.48Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy51.84Unverified
2ResNet18average top-1 classification accuracy51.67Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet18)Top-1 Accuracy93.18Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet18)Top-1 Accuracy71.61Unverified
#ModelMetricClaimedVerifiedStatus
1Hybrid BYOL-S/CvTAccuracy67.2Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet50)Top-1 Accuracy54.86Unverified