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 1451–1500 of 5044 papers

TitleStatusHype
Deep Learning with Tabular Data: A Self-supervised ApproachCode0
Deconstructing Denoising Diffusion Models for Self-Supervised LearningCode2
Deep Clustering with Diffused Sampling and Hardness-aware Self-distillationCode0
Adaptive Crowdsourcing Via Self-Supervised Learning—0
Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation ModelsCode0
Learning Representations for Clustering via Partial Information Discrimination and Cross-Level InteractionCode0
Towards Efficient and Effective Deep Clustering with Dynamic Grouping and Prototype AggregationCode0
LPNL: Scalable Link Prediction with Large Language Models—0
FedRSU: Federated Learning for Scene Flow Estimation on Roadside UnitsCode0
Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural CalibrationCode2
A Novel Garment Transfer Method Supervised by Distilled Knowledge of Virtual Try-on Model—0
Non-Neighbors Also Matter to Kriging: A New Contrastive-Prototypical LearningCode0
Detecting and recognizing characters in Greek papyri with YOLOv8, DeiT and SimCLR—0
SAM-dPCR: Real-Time and High-throughput Absolute Quantification of Biological Samples Using Zero-Shot Segment Anything Model—0
Self-Labeling the Job Shop Scheduling ProblemCode1
LW-FedSSL: Resource-efficient Layer-wise Federated Self-supervised Learning—0
Anisotropy Is Inherent to Self-Attention in Transformers—0
Memorization in Self-Supervised Learning Improves Downstream GeneralizationCode0
Data-driven grapheme-to-phoneme representations for a lexicon-free text-to-speech—0
LDReg: Local Dimensionality Regularized Self-Supervised LearningCode1
CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding—0
POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images—0
Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization—0
Revisiting Self-supervised Learning of Speech Representation from a Mutual Information Perspective—0
DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations without Text AlignmentCode2
How does self-supervised pretraining improve robustness against noisy labels across various medical image classification datasets?—0
Exploring Masked Autoencoders for Sensor-Agnostic Image Retrieval in Remote SensingCode1
Discovery of Generalizable TBI Phenotypes Using Multivariate Time-Series Clustering—0
Enhanced Few-Shot Class-Incremental Learning via Ensemble Models—0
Learning from Semi-Factuals: A Debiased and Semantic-Aware Framework for Generalized Relation Discovery—0
Self-supervised Learning of Dense Hierarchical Representations for Medical Image SegmentationCode0
Every Node is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph ClusteringCode1
EEGFormer: Towards Transferable and Interpretable Large-Scale EEG Foundation Model—0
Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMsCode3
Generative Deduplication For Socia Media Data Selection—0
Learning Performance-Oriented Control Barrier Functions Under Complex Safety Constraints and Limited ActuationCode0
HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion RecognitionCode2
Siamese Networks with Soft Labels for Unsupervised Lesion Detection and Patch Pretraining on Screening Mammograms—0
SwiMDiff: Scene-wide Matching Contrastive Learning with Diffusion Constraint for Remote Sensing Image—0
MISS: A Generative Pretraining and Finetuning Approach for Med-VQACode1
Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters—0
Singer Identity Representation Learning using Self-Supervised TechniquesCode2
Self-supervised Learning for Electroencephalogram: A Systematic Survey—0
TwinBooster: Synergising Large Language Models with Barlow Twins and Gradient Boosting for Enhanced Molecular Property PredictionCode0
Low-resource finetuning of foundation models beats state-of-the-art in histopathologyCode2
PhilEO Bench: Evaluating Geo-Spatial Foundation ModelsCode2
Autosen: improving automatic wifi human sensing through cross-modal autoencoder—0
Representation Learning for Wearable-Based Applications in the Case of Missing Data—0
Unifying Graph Contrastive Learning via Graph Message Augmentation—0
Primitive Geometry Segment Pre-training for 3D Medical Image SegmentationCode1
Show:102550
← PrevPage 30 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