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 3151–3200 of 5044 papers

TitleStatusHype
Features Based Adaptive Augmentation for Graph Contrastive LearningCode0
Federated Self-supervised Learning for Video UnderstandingCode1
Image Coding for Machines with Omnipotent Feature Learning—0
Approximating Discontinuous Nash Equilibrial Values of Two-Player General-Sum Differential Games—0
Masked Autoencoders in 3D Point Cloud Representation LearningCode1
S^5Mars: Semi-Supervised Learning for Mars Semantic Segmentation—0
Game State Learning via Game Scene Augmentation—0
Solutions for Fine-grained and Long-tailed Snake Species Recognition in SnakeCLEF 2022—0
Masked Self-Supervision for Remaining Useful Lifetime Prediction in Machine Tools—0
Task-oriented Self-supervised Learning for Anomaly Detection in ElectroencephalographyCode1
RIT Boston at SemEval-2022 Task 5: Multimedia Misogyny Detection By Using Coherent Visual and Language Features from CLIP Model and Data-centric AI Principle—0
Intent Detection and Discovery from User Logs via Deep Semi-Supervised Contrastive Clustering—0
Explicit Use of Topicality in Dialogue Response Generation—0
How Far Can I Go ? : A Self-Supervised Approach for Deterministic Video Depth ForecastingCode0
Masked Autoencoder for Self-Supervised Pre-training on Lidar Point CloudsCode1
Dissecting Self-Supervised Learning Methods for Surgical Computer VisionCode1
FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised LearningCode1
Self-Supervised Learning for Multimedia RecommendationCode1
FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition—0
TINC: Temporally Informed Non-Contrastive Learning for Disease Progression Modeling in Retinal OCT VolumesCode0
Learning Underrepresented Classes from Decentralized Partially Labeled Medical Images—0
No Reason for No Supervision: Improved Generalization in Supervised ModelsCode1
CONVIQT: Contrastive Video Quality EstimatorCode1
Interventional Contrastive Learning with Meta Semantic Regularizer—0
The THUEE System Description for the IARPA OpenASR21 Challenge—0
EBMs vs. CL: Exploring Self-Supervised Visual Pretraining for Visual Question Answering—0
SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous DrivingCode1
Comparison of Speech Representations for the MOS Prediction System—0
Automatic identification of segmentation errors for radiotherapy using geometric learningCode1
Guillotine Regularization: Why removing layers is needed to improve generalization in Self-Supervised Learning—0
Self-supervised Learning in Remote Sensing: A ReviewCode1
Wav2Vec-Aug: Improved self-supervised training with limited data—0
Wiener Graph Deconvolutional Network Improves Graph Self-Supervised LearningCode1
Vision Transformer for Contrastive ClusteringCode1
Self-Supervised 3D Monocular Object Detection by Recycling Bounding Boxes—0
SLIC: Self-Supervised Learning with Iterative Clustering for Human Action VideosCode1
Geometry Contrastive Learning on Heterogeneous GraphsCode0
Speech Quality Assessment through MOS using Non-Matching ReferencesCode1
Predicting within and across language phoneme recognition performance of self-supervised learning speech pre-trained modelsCode0
BYOL-S: Learning Self-supervised Speech Representations by BootstrappingCode1
Self Supervised Learning for Few Shot Hyperspectral Image Classification—0
Self-Supervised Training with Autoencoders for Visual Anomaly Detection—0
A Systematic Comparison of Phonetic Aware Techniques for Speech EnhancementCode1
Self-Supervised Learning of Brain Dynamics from Broad Neuroimaging DataCode1
TiCo: Transformation Invariance and Covariance Contrast for Self-Supervised Visual Representation LearningCode0
SCIM: Simultaneous Clustering, Inference, and Mapping for Open-World Semantic Scene UnderstandingCode0
Analysis of Self-Supervised Learning and Dimensionality Reduction Methods in Clustering-Based Active Learning for Speech Emotion RecognitionCode0
Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training—0
HealNet -- Self-Supervised Acute Wound Heal-Stage Classification—0
Few-Max: Few-Shot Domain Adaptation for Unsupervised Contrastive Representation LearningCode0
Show:102550
← PrevPage 64 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