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 4751–4800 of 5044 papers

TitleStatusHype
Learning to Exploit Temporal Structure for Biomedical Vision-Language ProcessingCode0
Learning to Edit Visual Programs with Self-SupervisionCode0
Learning Street View Representations with Spatiotemporal ContrastCode0
Self-Supervised Learning of 3D Human Pose using Multi-view GeometryCode0
Training Deep Networks from Zero to Hero: avoiding pitfalls and going beyondCode0
Training Frozen Feature Pyramid DINOv2 for Eyelid Measurements with Infinite Encoding and Orthogonal RegularizationCode0
Depth Contrast: Self-Supervised Pretraining on 3DPM Images for Mining Material ClassificationCode0
Demographic Predictability in 3D CT Foundation EmbeddingsCode0
Learning Soft Estimator of Keypoint Scale and Orientation With Probabilistic Covariant LossCode0
Learning Sentinel-2 reflectance dynamics for data-driven assimilation and forecastingCode0
Degradation Self-Supervised Learning for Lithium-ion Battery Health DiagnosticsCode0
Unsupervised End-to-End Training with a Self-Defined TargetCode0
Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers?Code0
Structure-preserving contrastive learning for spatial time seriesCode0
Self-supervised learning of audio representations using angular contrastive lossCode0
Learning Self-Regularized Adversarial Views for Self-Supervised Vision TransformersCode0
Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient EncoderCode0
DEGNN: Dual Experts Graph Neural Network Handling Both Edge and Node Feature NoiseCode0
Self-Supervised Learning of Color ConstancyCode0
A Unified and Scalable Membership Inference Method for Visual Self-supervised Encoder via Part-aware CapabilityCode0
Learning Representations for Clustering via Partial Information Discrimination and Cross-Level InteractionCode0
Self-supervised Learning of Contextualized Local Visual EmbeddingsCode0
Self-supervised Learning of Dense Hierarchical Representations for Medical Image SegmentationCode0
Self-supervised Learning of Dense Shape CorrespondenceCode0
Defense for Black-box Attacks on Anti-spoofing Models by Self-Supervised LearningCode0
Unsupervised Facial Expression Representation Learning with Contrastive Local WarpingCode0
Pose-Aware Self-Supervised Learning with Viewpoint Trajectory RegularizationCode0
Self-Supervised Learning of Depth and Motion Under Photometric InconsistencyCode0
Learning predictable and robust neural representations by straightening image sequencesCode0
Self-supervised Learning of Detailed 3D Face ReconstructionCode0
Style Transfer and Self-Supervised Learning Powered Myocardium Infarction Super-Resolution SegmentationCode0
Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervisionCode0
Deep Unsupervised Learning for 3D ALS Point Cloud Change DetectionCode0
Subgraph Gaussian Embedding Contrast for Self-Supervised Graph Representation LearningCode0
Learning Performance-Oriented Control Barrier Functions Under Complex Safety Constraints and Limited ActuationCode0
Identifying Latent Stochastic Differential EquationsCode0
Can Generative Models Improve Self-Supervised Representation Learning?Code0
Deep Spectral Improvement for Unsupervised Image Instance SegmentationCode0
Self-Supervised Learning of Face Representations for Video Face ClusteringCode0
BYEL : Bootstrap Your Emotion LatentCode0
Self-Supervised Learning of Generative Spin-Glasses with Normalizing FlowsCode0
DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD classification directly from H&E whole-slide images in colorectal and breast cancerCode0
SubOmiEmbed: Self-supervised Representation Learning of Multi-omics Data for Cancer Type ClassificationCode0
Deep self-supervised learning with visualisation for automatic gesture recognitionCode0
Self-supervised Learning of Image Embedding for Continuous ControlCode0
Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action RecognitionCode0
SubZero: Subspace Zero-Shot MRI ReconstructionCode0
Amortised Invariance Learning for Contrastive Self-SupervisionCode0
Deep Reinforcement Learning for Synthesizing Functions in Higher-Order LogicCode0
Learning from Synchronization: Self-Supervised Uncalibrated Multi-View Person Association in Challenging ScenesCode0
Show:102550
← PrevPage 96 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