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 4951–5000 of 5044 papers

TitleStatusHype
Information Competing Process for Learning Diversified RepresentationsCode0
Learning Representations by Maximizing Mutual Information Across ViewsCode0
Self-Supervised Representation Learning From Videos for Facial Action Unit DetectionCode0
Self-Supervised Representation Learning by Rotation Feature DecouplingCode0
Multi-Task Self-Supervised Object Detection via Recycling of Bounding Box Annotations—0
Putting An End to End-to-End: Gradient-Isolated Learning of RepresentationsCode0
Self-supervised audio representation learning for mobile devices—0
How to learn from unlabeled volume data: Self-Supervised 3D Context Feature Learning—0
Self-supervised learning of inverse problem solvers in medical imaging—0
Semi-Supervised Learning with Scarce AnnotationsCode0
Self-Supervised Similarity Learning for Digital Pathology—0
An Improved Self-supervised GAN via Adversarial Training—0
Learning by Inertia: Self-supervised Monocular Visual Odometry for Road Vehicles—0
Scaling and Benchmarking Self-Supervised Visual Representation LearningCode0
Self-supervised Learning for Video Correspondence FlowCode0
Object-Oriented Model Learning through Multi-Level Abstraction—0
A Model Cortical Network for Spatiotemporal Sequence Learning and Prediction—0
DynamoNet: Dynamic Action and Motion Network—0
SelFlow: Self-Supervised Learning of Optical FlowCode0
What I See Is What You See: Joint Attention Learning for First and Third Person Video Co-analysis—0
Suction Grasp Region Prediction using Self-supervised Learning for Object Picking in Dense Clutter—0
Temporal Cycle-Consistency LearningCode0
Object-Oriented Dynamics Learning through Multi-Level AbstractionCode0
Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight—0
Knowledge Distillation for Human Action Anticipation—0
Siamese Encoding and Alignment by Multiscale Learning with Self-Supervision—0
VideoBERT: A Joint Model for Video and Language Representation LearningCode0
MortonNet: Self-Supervised Learning of Local Features in 3D Point CloudsCode0
Self-Supervised Learning via Conditional Motion PropagationCode0
A Conceptual Bio-Inspired Framework for the Evolution of Artificial General IntelligenceCode0
3D Face Reconstruction from A Single Image Assisted by 2D Face Images in the WildCode0
Discovering Visual Patterns in Art Collections with Spatially-consistent Feature LearningCode0
Self-Supervised Learning of 3D Human Pose using Multi-view GeometryCode0
Self-Supervised Learning of Face Representations for Video Face ClusteringCode0
Self-supervised Learning for Single View Depth and Surface Normal Estimation—0
Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few LabelsCode0
Beyond Photometric Loss for Self-Supervised Ego-Motion EstimationCode0
Dense Depth Estimation in Monocular Endoscopy with Self-supervised Learning MethodsCode0
Exploiting Unlabeled Data in CNNs by Self-supervised Learning to RankCode0
Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey—0
Revisiting Self-Supervised Visual Representation LearningCode0
Self-Supervised Deep Learning on Point Clouds by Reconstructing Space—0
3D Human Pose Machines with Self-supervised LearningCode0
Neural Inverse Rendering of an Indoor Scene from a Single Image—0
Self-Supervised Learning from Web Data for Multimodal RetrievalCode0
Self-supervised Learning of Image Embedding for Continuous ControlCode0
Task-Free Continual LearningCode0
Self-Improving Visual Odometry—0
Self-supervised Learning of Dense Shape CorrespondenceCode0
Trading robust representations for sample complexity through self-supervised visual experience—0
Show:102550
← PrevPage 100 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