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 4851–4900 of 5044 papers

TitleStatusHype
Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis—0
Towards Lifelong Self-Supervision For Unpaired Image-to-Image TranslationCode0
Laplacian Denoising Autoencoder—0
Improving out-of-distribution generalization via multi-task self-supervised pretraining—0
A Collective Learning Framework to Boost GNN Expressiveness—0
Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows—0
Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels—0
Self-Supervised Contextual Bandits in Computer Vision—0
CPS++: Improving Class-level 6D Pose and Shape Estimation From Monocular Images With Self-Supervised Learning—0
Online Self-Supervised Learning for Object Picking: Detecting Optimum Grasping Position using a Metric Learning Approach—0
Self-Supervised Visual Learning by Variable Playback Speeds Prediction of a VideoCode0
A Survey on Deep Hashing Methods—0
A Self-Supervised Learning Approach to Rapid Path Planning for Car-Like Vehicles Maneuvering in Urban EnvironmentCode0
Self-supervised Representation Learning for Ultrasound Video—0
A Multi-view Perspective of Self-supervised Learning—0
Disentangled Speech Embeddings using Cross-modal Self-supervision—0
Self-supervised learning for audio-visual speaker diarization—0
Self-supervised visual feature learning with curriculumCode0
Visually Guided Self Supervised Learning of Speech Representations—0
Semi-supervised Learning via Conditional Rotation Angle Estimation—0
Robust Self-Supervised Learning of Deterministic Errors in Single-Plane (Monoplanar) and Dual-Plane (Biplanar) X-ray Fluoroscopy—0
Self-Supervised Learning of Generative Spin-Glasses with Normalizing FlowsCode0
Learning Compound Tasks without Task-specific Knowledge via Imitation and Self-supervised Learning—0
Test-Time Training for Generalization under Distribution Shifts—0
Conditional Augmentation for Generative Modeling—0
A simple baseline for domain adaptation using rotation prediction—0
Image Enhanced Rotation Prediction for Self-Supervised Learning—0
Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model—0
Self-Supervised Learning of Physics-Guided Reconstruction Neural Networks without Fully-Sampled Reference DataCode0
Multimodal Self-Supervised Learning for Medical Image Analysis—0
To Balance or Not to Balance: A Simple-yet-Effective Approach for Learning with Long-Tailed Distributions—0
Self-supervised Object Motion and Depth Estimation from Video—0
Self-Supervised 3D Keypoint Learning for Ego-motion EstimationCode0
Self-Supervised Learning of Video-Induced Visual Invariances—0
Self-Supervised Contextual Language Representation of Radiology Reports to Improve the Identification of Communication Urgency—0
Exploiting Motion Information from Unlabeled Videos for Static Image Action Recognition—0
Self-Supervised Learning by Cross-Modal Audio-Video ClusteringCode0
Invenio: Discovering Hidden Relationships Between Tasks/Domains Using Structured Meta Learning—0
SelfVIO: Self-Supervised Deep Monocular Visual-Inertial Odometry and Depth Estimation—0
Self-supervised Learning of 3D Objects from Natural Images—0
AETv2: AutoEncoding Transformations for Self-Supervised Representation Learning by Minimizing Geodesic Distances in Lie Groups—0
Self-supervised Adversarial TrainingCode0
Self-Supervised Learning of State Estimation for Manipulating Deformable Linear Objects—0
Self-Supervised Learning For Few-Shot Image ClassificationCode0
Self-supervised representation learning from electroencephalography signalsCode0
Unsupervised Domain Adaptation of Contextual Embeddings for Low-Resource Duplicate Question Detection—0
Self-supervised learning of class embeddings from video—0
Self-supervised Learning of Detailed 3D Face ReconstructionCode0
SPICE: Self-supervised Pitch Estimation—0
Learning audio representations via phase prediction—0
Show:102550
← PrevPage 98 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