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 3851–3900 of 5044 papers

TitleStatusHype
Towards Demystifying Representation Learning with Non-contrastive Self-supervisionCode0
SignBERT: Pre-Training of Hand-Model-Aware Representation for Sign Language Recognition—0
K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and SyllablesCode1
Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition—0
Self-supervised Learning is More Robust to Dataset ImbalanceCode1
Neural Algorithmic Reasoners are Implicit Planners—0
Digging Into Self-Supervised Learning of Feature Descriptors—0
Colour augmentation for improved semi-supervised semantic segmentation—0
RPT: Toward Transferable Model on Heterogeneous Researcher Data via Pre-TrainingCode0
SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation LearningCode1
Self-supervised Speaker Recognition with Loss-gated LearningCode1
VieSum: How Robust Are Transformer-based Models on Vietnamese Summarization?—0
3D Infomax improves GNNs for Molecular Property PredictionCode1
Pre-training Molecular Graph Representation with 3D GeometryCode1
Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models—0
AnoSeg: Anomaly Segmentation Network Using Self-Supervised Learning—0
3D Unsupervised Region-Aware Registration Transformer—0
Self-Supervised Knowledge Assimilation for Expert-Layman Text Style TransferCode0
The Power of Contrast for Feature Learning: A Theoretical Analysis—0
Exploring the Common Principal Subspace of Deep Features in Neural Networks—0
SSFL: Tackling Label Deficiency in Federated Learning via Personalized Self-Supervision—0
Self-Supervised Learning of Perceptually Optimized Block Motion Estimates for Video Compression—0
Self-Supervised Generative Style Transfer for One-Shot Medical Image SegmentationCode1
Unsupervised Speech Segmentation and Variable Rate Representation Learning using Segmental Contrastive Predictive Coding—0
Wireless Link Scheduling via Graph Representation Learning: A Comparative Study of Different Supervision LevelsCode0
How You Move Your Head Tells What You Do: Self-supervised Video Representation Learning with Egocentric Cameras and IMU Sensors—0
Consistency Regularization Can Improve Robustness to Label Noise—0
Multi-task Voice Activated Framework using Self-supervised Learning—0
Motif-based Graph Self-Supervised Learning for Molecular Property PredictionCode1
Stochastic Contrastive Learning—0
Incremental Layer-wise Self-Supervised Learning for Efficient Speech Domain Adaptation On Device—0
Evaluating the fairness of fine-tuning strategies in self-supervised learning—0
Learning of Inter-Label Geometric Relationships Using Self-Supervised Learning: Application To Gleason Grade Segmentation—0
DualNet: Continual Learning, Fast and SlowCode1
Consistent Explanations by Contrastive LearningCode1
A Survey of Knowledge Enhanced Pre-trained Models—0
Noise2Recon: Enabling Joint MRI Reconstruction and Denoising with Semi-Supervised and Self-Supervised LearningCode1
Mining for Strong Gravitational Lenses with Self-supervised LearningCode1
CoSeg: Cognitively Inspired Unsupervised Generic Event SegmentationCode0
Biologically Plausible Training Mechanisms for Self-Supervised Learning in Deep NetworksCode0
Towards Better Understanding and Better Generalization of Low-shot Classification in Histology Images with Contrastive Learning—0
Contrastive Learning of 3D Shape Descriptor with Dynamic Adversarial Views—0
Residual Contrastive Learning: Unsupervised Representation Learning from Residuals—0
Prototypical Contrastive Predictive Coding—0
Self-supervised Learning for Sequential Recommendation with Model Augmentation—0
Lifting Imbalanced Regression with Self-Supervised Learning—0
Learning Universal User Representations via Self-Supervised Lifelong Behaviors Modeling—0
Self-Supervised Structured Representations for Deep Reinforcement Learning—0
Hierarchical Cross Contrastive Learning of Visual Representations—0
FROB: Few-shot ROBust Model for Classification with Out-of-Distribution Detection—0
Show:102550
← PrevPage 78 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