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 1401–1450 of 5044 papers

TitleStatusHype
Self-Supervised Learning for Domain Adaptation on Point-CloudsCode1
Exploit Clues from Views: Self-Supervised and Regularized Learning for Multiview Object RecognitionCode1
Temporally Coherent Embeddings for Self-Supervised Video Representation LearningCode1
Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural NetworksCode1
On Compositions of Transformations in Contrastive Self-Supervised LearningCode1
MVP: Unified Motion and Visual Self-Supervised Learning for Large-Scale Robotic NavigationCode1
Self-supervised Image Enhancement Network: Training with Low Light Images OnlyCode1
Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-trainingCode1
Learning Dynamic Belief Graphs to Generalize on Text-Based GamesCode1
CoLES: Contrastive Learning for Event Sequences with Self-SupervisionCode1
BADGR: An Autonomous Self-Supervised Learning-Based Navigation SystemCode1
Automatically Discovering and Learning New Visual Categories with Ranking StatisticsCode1
Deep Self-Supervised Representation Learning for Free-Hand SketchCode1
Multi-task self-supervised learning for Robust Speech RecognitionCode1
A Large Scale Event-based Detection Dataset for AutomotiveCode1
CONSAC: Robust Multi-Model Fitting by Conditional Sample ConsensusCode1
Video Cloze Procedure for Self-Supervised Spatio-Temporal LearningCode1
AeroRIT: A New Scene for Hyperspectral Image AnalysisCode1
Self-Supervised Learning of Pretext-Invariant RepresentationsCode1
Self-labelling via simultaneous clustering and representation learningCode1
PRNet: Self-Supervised Learning for Partial-to-Partial RegistrationCode1
Animating Landscape: Self-Supervised Learning of Decoupled Motion and Appearance for Single-Image Video SynthesisCode1
Self-supervised Learning for ECG-based Emotion RecognitionCode1
vq-wav2vec: Self-Supervised Learning of Discrete Speech RepresentationsCode1
TabNet: Attentive Interpretable Tabular LearningCode1
Models Genesis: Generic Autodidactic Models for 3D Medical Image AnalysisCode1
Charting the Right Manifold: Manifold Mixup for Few-shot LearningCode1
Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich TasksCode1
Bidirectional Learning for Domain Adaptation of Semantic SegmentationCode1
Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich TasksCode1
Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised LearningCode1
Self-supervised learning of a facial attribute embedding from videoCode1
ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo SystemsCode1
CR-GAN: Learning Complete Representations for Multi-view GenerationCode1
Digging Into Self-Supervised Monocular Depth EstimationCode1
Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum LearningCode1
Time-Contrastive Networks: Self-Supervised Learning from VideoCode1
A Semi-Supervised Learning Method for the Identification of Bad Exposures in Large Imaging Surveys—0
Self-supervised Learning on Camera Trap Footage Yields a Strong Universal Face Embedder—0
Speech Quality Assessment Model Based on Mixture of Experts: System-Level Performance Enhancement and Utterance-Level Challenge Analysis—0
World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World ModelCode0
ShapeEmbed: a self-supervised learning framework for 2D contour quantification—0
RetFiner: A Vision-Language Refinement Scheme for Retinal Foundation ModelsCode0
Continual Self-Supervised Learning with Masked Autoencoders in Remote Sensing—0
Hybrid Deep Learning and Signal Processing for Arabic Dialect Recognition in Low-Resource Settings—0
Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud RecognitionCode0
Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer FeaturesCode0
Opportunistic Osteoporosis Diagnosis via Texture-Preserving Self-Supervision, Mixture of Experts and Multi-Task Integration—0
TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis—0
FixCLR: Negative-Class Contrastive Learning for Semi-Supervised Domain Generalization—0
Show:102550
← PrevPage 29 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