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 1301–1350 of 5044 papers

TitleStatusHype
Combining Self-Training and Self-Supervised Learning for Unsupervised Disfluency DetectionCode1
Multimodal Emotion Recognition with Transformer-Based Self Supervised Feature FusionCode1
Pre-training Text-to-Text Transformers for Concept-centric Common SenseCode1
BARThez: a Skilled Pretrained French Sequence-to-Sequence ModelCode1
Graph Contrastive Learning with AugmentationsCode1
Self-Alignment Pretraining for Biomedical Entity RepresentationsCode1
Self-supervised Graph Learning for RecommendationCode1
Understanding YouTube Communities via Subscription-based Channel EmbeddingsCode1
Representation Learning via Invariant Causal MechanismsCode1
MixCo: Mix-up Contrastive Learning for Visual RepresentationCode1
Measuring Visual Generalization in Continuous Control from PixelsCode1
MS^2L: Multi-Task Self-Supervised Learning for Skeleton Based Action RecognitionCode1
Guiding Attention for Self-Supervised Learning with TransformersCode1
XDA: Accurate, Robust Disassembly with Transfer LearningCode1
Hard Negative Mixing for Contrastive LearningCode1
Self-Supervised Few-Shot Learning on Point CloudsCode1
G-SimCLR: Self-Supervised Contrastive Learning with Guided Projection via Pseudo LabellingCode1
An Unsupervised Sentence Embedding Method by Mutual Information MaximizationCode1
Sub-graph Contrast for Scalable Self-Supervised Graph Representation LearningCode1
MoPro: Webly Supervised Learning with Momentum PrototypesCode1
SelfAugment: Automatic Augmentation Policies for Self-Supervised LearningCode1
Boosting Generalization in Bio-Signal Classification by Learning the Phase-Amplitude CouplingCode1
Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation LearningCode1
A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-IdentificationCode1
Unpaired Learning of Deep Image DenoisingCode1
Self-Supervised Learning for Large-Scale Unsupervised Image ClusteringCode1
S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information MaximizationCode1
Self-Supervised Learning for Monocular Depth Estimation from Aerial ImageryCode1
Neutral Face Game Character Auto-Creation via PokerFace-GANCode1
Reversing the cycle: self-supervised deep stereo through enhanced monocular distillationCode1
Jointly Fine-Tuning “BERT-like” Self Supervised Models to Improve Multimodal Speech Emotion RecognitionCode1
Self-adapting confidence estimation for stereoCode1
Self-Supervised Learning of Audio-Visual Objects from VideoCode1
Spatiotemporal Contrastive Video Representation LearningCode1
Self-supervised learning using consistency regularization of spatio-temporal data augmentation for action recognitionCode1
Self-supervised Object Tracking with Cycle-consistent Siamese NetworksCode1
Memory-augmented Dense Predictive Coding for Video Representation LearningCode1
Self-supervised Learning of Point Clouds via Orientation EstimationCode1
Distilling Visual Priors from Self-Supervised LearningCode1
Self-supervised learning through the eyes of a childCode1
Uncovering the structure of clinical EEG signals with self-supervised learningCode1
KOVIS: Keypoint-based Visual Servoing with Zero-Shot Sim-to-Real Transfer for Robotics ManipulationCode1
3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised LearningCode1
Crowdsourced 3D Mapping: A Combined Multi-View Geometry and Self-Supervised Learning ApproachCode1
Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry ConsistencyCode1
Reliable Label Bootstrapping for Semi-Supervised LearningCode1
Weakly and Partially Supervised Learning Frameworks for Anomaly DetectionCode1
CrossTransformers: spatially-aware few-shot transferCode1
Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous NetworksCode1
Feature-metric Loss for Self-supervised Learning of Depth and EgomotionCode1
Show:102550
← PrevPage 27 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