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 4601–4650 of 5044 papers

TitleStatusHype
Shot in the Dark: Few-Shot Learning with No Base-Class Labels—0
Guiding Attention for Self-Supervised Learning with TransformersCode1
EqCo: Equivalent Rules for Self-supervised Contrastive LearningCode0
Learning Complete 3D Morphable Face Models from Images and Videos—0
MDReg-Net: Multi-resolution diffeomorphic image registration using fully convolutional networks with deep self-supervision—0
Remote Sensing Image Scene Classification with Self-Supervised Paradigm under Limited Labeled Samples—0
XDA: Accurate, Robust Disassembly with Transfer LearningCode1
Hard Negative Mixing for Contrastive LearningCode1
Understanding Self-supervised Learning with Dual Deep NetworksCode0
Adversarial Semi-Supervised Multi-Domain Tracking—0
Self-Supervised Few-Shot Learning on Point CloudsCode1
On Size Generalization in Graph Neural Networks—0
G-SimCLR: Self-Supervised Contrastive Learning with Guided Projection via Pseudo LabellingCode1
Sense and Learn: Self-Supervision for Omnipresent Sensors—0
Clustering-based Unsupervised Generative Relation Extraction—0
An Unsupervised Sentence Embedding Method by Mutual Information MaximizationCode1
Neural Identification for ControlCode0
Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motion—0
Sub-graph Contrast for Scalable Self-Supervised Graph Representation LearningCode1
Conditional Hybrid GAN for Sequence Generation—0
Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy—0
MoPro: Webly Supervised Learning with Momentum PrototypesCode1
Learning to Identify Physical Parameters from Video Using Differentiable Physics—0
AAG: Self-Supervised Representation Learning by Auxiliary Augmentation with GNT-Xent LossCode0
Online Semi-Supervised Learning in Contextual Bandits with Episodic RewardCode0
SelfAugment: Automatic Augmentation Policies for Self-Supervised LearningCode1
Boosting Generalization in Bio-Signal Classification by Learning the Phase-Amplitude CouplingCode1
Cascade Network for Self-Supervised Monocular Depth Estimation—0
Contrastive Self-supervised Learning for Graph Classification—0
Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation LearningCode1
Dialogue-adaptive Language Model Pre-training From Quality EstimationCode0
Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformations—0
A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-IdentificationCode1
A Framework For Contrastive Self-Supervised Learning And Designing A New ApproachCode4
Connecting Web Event Forecasting with Anomaly Detection: A Case Study on Enterprise Web Applications Using Self-Supervised Neural Networks—0
Unpaired Learning of Deep Image DenoisingCode1
Self-Supervised Learning Based on Spatial Awareness for Medical Image AnalysisCode0
Puzzle-AE: Novelty Detection in Images through Solving PuzzlesCode0
Confidence-aware Adversarial Learning for Self-supervised Semantic MatchingCode0
Learning to Learn in a Semi-Supervised Fashion—0
Contrastive learning, multi-view redundancy, and linear models—0
Self-Supervised Learning for Large-Scale Unsupervised Image ClusteringCode1
Few-Shot Image Classification via Contrastive Self-Supervised Learning—0
S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information MaximizationCode1
Reversing the cycle: self-supervised deep stereo through enhanced monocular distillationCode1
Fast and Robust Face-to-Parameter Translation for Game Character Auto-Creation—0
Self-Supervised Learning for Monocular Depth Estimation from Aerial ImageryCode1
Neutral Face Game Character Auto-Creation via PokerFace-GANCode1
A Self-supervised GAN for Unsupervised Few-shot Object Recognition—0
Jointly Fine-Tuning “BERT-like” Self Supervised Models to Improve Multimodal Speech Emotion RecognitionCode1
Show:102550
← PrevPage 93 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