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 5001–5044 of 5044 papers

TitleStatusHype
Self-Supervised Learning of Depth and Camera Motion from 360° Videos—0
Cross and Learn: Cross-Modal Self-SupervisionCode0
Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension—0
Improving label efficiency through multi-task learning on auditory data—0
AIRNet: Self-Supervised Affine Registration for 3D Medical Images using Neural Networks—0
Improving Sentence Representations with Consensus Maximisation—0
Meta-Embedding as Auxiliary Task Regularization—0
Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition—0
Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning—0
Cross Pixel Optical Flow Similarity for Self-Supervised Learning—0
TextTopicNet - Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text SpacesCode0
Self-supervised Learning for Dense Depth Estimation in Monocular Endoscopy—0
The Sparse Manifold Transform—0
Temporal coherence-based self-supervised learning for laparoscopic workflow analysisCode0
Two Stream Self-Supervised Learning for Action Recognition—0
Self-Supervised Feature Learning by Learning to Spot Artifacts—0
Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning—0
Boosting Self-Supervised Learning via Knowledge Transfer—0
Better and Faster: Knowledge Transfer from Multiple Self-supervised Learning Tasks via Graph Distillation for Video Classification—0
Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection—0
Fusion of stereo and still monocular depth estimates in a self-supervised learning context—0
Reblur2Deblur: Deblurring Videos via Self-Supervised Learning—0
Non-Rigid Image Registration Using Self-Supervised Fully Convolutional Networks without Training Data—0
Self-Supervised Learning of Object Motion Through Adversarial Video Prediction—0
Self-supervised Learning of Motion CaptureCode0
Exploiting the potential of unlabeled endoscopic video data with self-supervised learning—0
Improvements to context based self-supervised learning—0
Self-supervised learning: When is fusion of the primary and secondary sensor cue useful?—0
Generating Music Medleys via Playing Music Puzzle Games—0
Self-Supervised Learning for Stereo Matching with Self-Improving Ability—0
Transitive Invariance for Self-supervised Visual Representation Learning—0
Weakly- and Self-Supervised Learning for Content-Aware Deep Image RetargetingCode0
Self-supervised Learning of Pose Embeddings from Spatiotemporal Relations in Videos—0
CASSL: Curriculum Accelerated Self-Supervised Learning—0
Self-Supervised Learning for Spinal MRIs—0
LSTM Self-Supervision for Detailed Behavior Analysis—0
Towards Visual Ego-motion Learning in Robots—0
Self-supervised learning of visual features through embedding images into text topic spaces—0
Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human ParsingCode0
A Self-supervised Learning System for Object Detection using Physics Simulation and Multi-view Pose EstimationCode0
Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation—0
Diverse Sampling for Self-Supervised Learning of Semantic Segmentation—0
Self-Supervised Video Representation Learning With Odd-One-Out Networks—0
Wikipedia Edit Number Prediction based on Temporal Dynamics OnlyCode0
Show:102550
← PrevPage 101 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