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 4101–4150 of 5044 papers

TitleStatusHype
Coherent, super resolved radar beamforming using self-supervised learning—0
Trainable Class Prototypes for Few-Shot Learning—0
Self-Supervised Tracking via Target-Aware Data Synthesis—0
SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving—0
Improving Ultrasound Tongue Image Reconstruction from Lip Images Using Self-supervised Learning and Attention Mechanism—0
Global and Local Contrastive Self-Supervised Learning for Semantic Segmentation of HR Remote Sensing Images—0
Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy—0
Prototype Augmentation and Self-Supervision for Incremental Learning—0
Safe Local Motion Planning With Self-Supervised Freespace ForecastingCode1
Self-Supervised Learning on 3D Point Clouds by Learning Discrete Generative Models—0
Learning Spatial-Semantic Relationship for Facial Attribute Recognition With Limited Labeled Data—0
Partial Person Re-Identification With Part-Part Correspondence Learning—0
Spatio-temporal Contrastive Domain Adaptation for Action Recognition—0
Self-Supervised Wasserstein Pseudo-Labeling for Semi-Supervised Image Classification—0
Self-supervised Video Representation Learning with Cross-Stream Prototypical ContrastingCode1
Novelty Detection via Contrastive Learning with Negative Data Augmentation—0
Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Images—0
A Random CNN Sees Objects: One Inductive Bias of CNN and Its ApplicationsCode1
A Self-supervised Method for Entity AlignmentCode1
Self-Supervised GANs with Label AugmentationCode1
Watching Too Much Television is Good: Self-Supervised Audio-Visual Representation Learning from Movies and TV Shows—0
LiRA: Learning Visual Speech Representations from Audio through Self-supervision—0
Nonequilibrium thermodynamics of self-supervised learning—0
ATD: Augmenting CP Tensor Decomposition by Self SupervisionCode1
Self-Supervised Learning with Kernel Dependence MaximizationCode1
Interpretable Self-supervised Multi-task Learning for COVID-19 Information Retrieval and Extraction—0
Revisiting Model Stitching to Compare Neural Representations—0
Delving Deep into the Generalization of Vision Transformers under Distribution ShiftsCode1
SAS: Self-Augmentation Strategy for Language Model Pre-trainingCode0
Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability PerspectiveCode1
Pre-Trained Models: Past, Present and Future—0
D2C: Diffusion-Denoising Models for Few-shot Conditional GenerationCode1
ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction—0
Self-supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection—0
Graph Contrastive Learning AutomatedCode1
PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition—0
Cross-Modal Discrete Representation Learning—0
Revisiting Contrastive Methods for Unsupervised Learning of Visual RepresentationsCode2
MST: Masked Self-Supervised Transformer for Visual Representation—0
Cross-domain Contrastive Learning for Unsupervised Domain AdaptationCode0
Automated Self-Supervised Learning for GraphsCode1
Adversarial Graph Augmentation to Improve Graph Contrastive LearningCode1
Self-supervision of Feature Transformation for Further Improving Supervised Learning—0
Self-supervised Feature Enhancement: Applying Internal Pretext Task to Supervised Learning—0
Self-Supervised Graph Learning with Hyperbolic Embedding for Temporal Health Event PredictionCode1
Self-Supervised Learning with Data Augmentations Provably Isolates Content from StyleCode1
Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive LossCode1
Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision MakingCode0
Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain AdaptationCode1
Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation—0
Show:102550
← PrevPage 83 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