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 4901–4950 of 5044 papers

TitleStatusHype
Self-supervised Feature Learning for 3D Medical Images by Playing a Rubik's Cube—0
Self-supervised learning for autonomous vehicles perception: A conciliation between analytical and learning methods—0
Digging Into Self-Supervised Monocular Depth EstimationCode0
Self-Supervised Representation Learning From Multi-Domain Data—0
MLSL: Multi-Level Self-Supervised Learning for Domain Adaptation with Spatially Independent and Semantically Consistent LabelingCode0
Test-Time Training with Self-Supervision for Generalization under Distribution ShiftsCode0
Self-Supervised Learning of Depth and Ego-motion with Differentiable Bundle Adjustment—0
Joint-task Self-supervised Learning for Temporal CorrespondenceCode0
ALBERT: A Lite BERT for Self-supervised Learning of Language RepresentationsCode2
Test-Time Training for Out-of-Distribution Generalization—0
PatchFormer: A neural architecture for self-supervised representation learning on images—0
Self-Supervised Learning of Depth and Motion Under Photometric InconsistencyCode0
Self-Supervised Monocular Depth HintsCode0
White-Box Adversarial Defense via Self-Supervised Data EstimationCode0
Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal GenerationCode0
Video Representation Learning by Dense Predictive CodingCode0
Self-supervised Dense 3D Reconstruction from Monocular Endoscopic Video—0
Self-supervised blur detection from synthetically blurred scenesCode0
Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry—0
TabNet: Attentive Interpretable Tabular LearningCode1
Models Genesis: Generic Autodidactic Models for 3D Medical Image AnalysisCode1
Multi-Task Self-Supervised Learning for Disfluency Detection—0
Neural Blind Deconvolution Using Deep PriorsCode0
Self-Supervised Learning for Stereo Reconstruction on Aerial Images—0
Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich TasksCode1
Charting the Right Manifold: Manifold Mixup for Few-shot LearningCode1
Multi-task Self-Supervised Learning for Human Activity Detection—0
Accurate and Robust Pulmonary Nodule Detection by 3D Feature Pyramid Network with Self-supervised Feature Learning—0
Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera—0
Self-supervised Learning with Physics-aware Neural Networks I: Galaxy Model Fitting—0
Self-supervised Learning of Distance Functions for Goal-Conditioned Reinforcement Learning—0
Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Prediction—0
Self-supervised Learning of Interpretable Keypoints from Unlabelled Videos—0
Self-supervised Hyperspectral Image Restoration using Separable Image Prior—0
Self-Supervised Dialogue Learning—0
Using Self-Supervised Learning Can Improve Model Robustness and UncertaintyCode0
LPaintB: Learning to Paint from Self-Supervision—0
Boosting Supervision with Self-Supervision for Few-shot Learning—0
Learning Video Representations using Contrastive Bidirectional Transformer—0
Boosting Few-Shot Visual Learning with Self-SupervisionCode0
Self-Supervised Learning for Contextualized Extractive SummarizationCode0
Information Competing Process for Learning Diversified RepresentationsCode0
Learning Representations by Maximizing Mutual Information Across ViewsCode0
Self-Supervised Representation Learning by Rotation Feature DecouplingCode0
Self-Supervised Representation Learning From Videos for Facial Action Unit DetectionCode0
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
Show:102550
← PrevPage 99 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