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
Harnessing Event Sensory Data for Error Pattern Prediction in Vehicles: A Language Model ApproachCode0
Harmony: A Joint Self-Supervised and Weakly-Supervised Framework for Learning General Purpose Visual RepresentationsCode0
Whitening Consistently Improves Self-Supervised LearningCode0
Test-Time Training with Self-Supervision for Generalization under Distribution ShiftsCode0
Contrastive Learning for OOD in Object detectionCode0
AC-Norm: Effective Tuning for Medical Image Analysis via Affine Collaborative NormalizationCode0
A CNN-Transformer for Classification of Longitudinal 3D MRI Images -- A Case Study on Hepatocellular Carcinoma PredictionCode0
Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot LearningCode0
As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learningCode0
Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational ReasoningCode0
Unbiased and Robust: External Attention-enhanced Graph Contrastive Learning for Cross-domain Sequential RecommendationCode0
TextTopicNet - Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text SpacesCode0
Beyond Random Augmentations: Pretraining with Hard ViewsCode0
VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge InjectionCode0
HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of ActionsCode0
GSIFN: A Graph-Structured and Interlaced-Masked Multimodal Transformer-based Fusion Network for Multimodal Sentiment AnalysisCode0
Are Data-driven Explanations Robust against Out-of-distribution Data?Code0
Putting An End to End-to-End: Gradient-Isolated Learning of RepresentationsCode0
GraSSRep: Graph-Based Self-Supervised Learning for Repeat Detection in Metagenomic AssemblyCode0
Self-supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and BeyondCode0
Contrastive Learning for Object DetectionCode0
That Sounds Right: Auditory Self-Supervision for Dynamic Robot ManipulationCode0
Self-supervised visual feature learning with curriculumCode0
Self-supervised Visualisation of Medical Image DatasetsCode0
Contrastive Learning for Lane Detection via cross-similarityCode0
Self-supervised visual learning from interactions with objectsCode0
A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature ExtractorsCode0
Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning?Code0
Biologically Plausible Training Mechanisms for Self-Supervised Learning in Deep NetworksCode0
Graph Self-Supervised Learning with Learnable Structural and Positional EncodingsCode0
Bilingual Dual-Head Deep Model for Parkinson's Disease Detection from SpeechCode0
Contrastive Adaptive Propagation Graph Neural Networks for Efficient Graph LearningCode0
The Common Stability Mechanism behind most Self-Supervised Learning ApproachesCode0
GraphVICRegHSIC: Towards improved self-supervised representation learning for graphs with a hyrbid loss functionCode0
Adversarial Bootstrapped Question Representation Learning for Knowledge TracingCode0
Continuous max-flow augmentation of self-supervised few-shot learning on SPECT left ventriclesCode0
Advancing Video Self-Supervised Learning via Image Foundation ModelsCode0
Continual Learning on Noisy Data Streams via Self-Purified ReplayCode0
Variational Graph Contrastive LearningCode0
Self-Supervision Enhances Instance-based Multiple Instance Learning Methods in Digital Pathology: A Benchmark StudyCode0
The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that MatterCode0
Self-Supervision in Time for Satellite Images(S3-TSS): A novel method of SSL technique in Satellite imagesCode0
Continual Contrastive Learning for Image ClassificationCode0
The Far Side of Failure: Investigating the Impact of Speech Recognition Errors on Subsequent Dementia ClassificationCode0
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