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

Showing 34513500 of 5044 papers

TitleStatusHype
Learning neural audio features without supervision0
Learning Optical Flow, Depth, and Scene Flow without Real-World Labels0
S2-Net: Self-supervision Guided Feature Representation Learning for Cross-Modality Images0
Learning Where to Learn in Cross-View Self-Supervised LearningCode1
Frame-wise Action Representations for Long Videos via Sequence Contrastive LearningCode1
Investigating Active-learning-based Training Data Selection for Speech Spoofing Countermeasure0
Curriculum learning for self-supervised speaker verification0
Audio-Adaptive Activity Recognition Across Video DomainsCode1
Mugs: A Multi-Granular Self-Supervised Learning FrameworkCode1
How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?Code1
3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point CloudsCode1
Contrastive Graph Learning for Population-based fMRI ClassificationCode1
Improving Contrastive Learning with Model AugmentationCode1
Intelligent Masking: Deep Q-Learning for Context Encoding in Medical Image AnalysisCode0
Self-supervised Semantic Segmentation Grounded in Visual Concepts0
Semi-supervised machine learning model for analysis of nanowire morphologies from transmission electron microscopy imagesCode0
DeLoRes: Decorrelating Latent Spaces for Low-Resource Audio Representation LearningCode1
Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation OverlapCode1
Tackling Online One-Class Incremental Learning by Removing Negative Contrasts0
CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from ImageCode1
What to Hide from Your Students: Attention-Guided Masked Image ModelingCode1
Learning Scene Flow in 3D Point Clouds with Noisy Pseudo Labels0
The Challenges of Continuous Self-Supervised Learning0
Negative Selection by Clustering for Contrastive Learning in Human Activity Recognition0
Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake DetectionCode1
Interpretable Prediction of Lung Squamous Cell Carcinoma Recurrence With Self-supervised LearningCode1
Self-Supervised Robust Scene Flow Estimation via the Alignment of Probability Density Functions0
Unifying Motion Deblurring and Frame Interpolation with EventsCode1
Text Transformations in Contrastive Self-Supervised Learning: A Review0
Federated Self-Supervised Learning for Acoustic Event Classification0
Representation Uncertainty in Self-Supervised Learning as Variational Inference0
Channel Self-Supervision for Online Knowledge Distillation0
Self-supervision through Random Segments with Autoregressive Coding (RandSAC)0
Language modeling via stochastic processesCode1
Masked Discrimination for Self-Supervised Learning on Point CloudsCode1
Dense Siamese Network for Dense Unsupervised LearningCode1
Unsupervised Network Embedding Beyond HomophilyCode1
Longitudinal Self-Supervision for COVID-19 Pathology Quantification0
Occlusion-Aware Self-Supervised Monocular 6D Object Pose EstimationCode1
Inferring topological transitions in pattern-forming processes with self-supervised learningCode0
Rethinking the optimization process for self-supervised model-driven MRI reconstruction0
View-Consistent Heterogeneous Network on Graphs With Few Labeled NodesCode1
GATE: Graph CCA for Temporal SElf-supervised Learning for Label-efficient fMRI AnalysisCode1
DATA: Domain-Aware and Task-Aware Self-supervised LearningCode1
Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot LearningCode1
Contrastive Learning with Positive-Negative Frame Mask for Music Representation0
Object discovery and representation networksCode0
Weak Augmentation Guided Relational Self-Supervised LearningCode1
Self-Supervised Deep Learning to Enhance Breast Cancer Detection on Screening Mammography0
Pushing the limits of raw waveform speaker recognitionCode3
Show:102550
← PrevPage 70 of 101Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Pretraining: NoneImages & Text57.5Unverified
2Pretraining: ShEDImages & Text54.3Unverified
3Pretraining: e-MixImages & Text48.9Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50Accuracy91.7Unverified
2ResNet18Accuracy91.02Unverified
3MV-MRAccuracy89.67Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy93.89Unverified
2ResNet18average top-1 classification accuracy92.58Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy72.51Unverified
2ResNet18average top-1 classification accuracy69.31Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet50)Top-1 Accuracy82.64Unverified
2CorInfomax (ResNet18)Top-1 Accuracy80.48Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy51.84Unverified
2ResNet18average top-1 classification accuracy51.67Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet18)Top-1 Accuracy93.18Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet18)Top-1 Accuracy71.61Unverified
#ModelMetricClaimedVerifiedStatus
1Hybrid BYOL-S/CvTAccuracy67.2Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet50)Top-1 Accuracy54.86Unverified