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 251–300 of 5044 papers

TitleStatusHype
ModalTune: Fine-Tuning Slide-Level Foundation Models with Multi-Modal Information for Multi-task Learning in Digital Pathology—0
Measuring the Robustness of Audio Deepfake DetectorsCode0
Learning to Efficiently Adapt Foundation Models for Self-Supervised Endoscopic 3D Scene Reconstruction from Any Cameras—0
Sonata: Self-Supervised Learning of Reliable Point RepresentationsCode4
Structured-Noise Masked Modeling for Video, Audio and Beyond—0
When the Future Becomes the Past: Taming Temporal Correspondence for Self-supervised Video Representation LearningCode1
1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities—0
Conjuring Positive Pairs for Efficient Unification of Representation Learning and Image Synthesis—0
SemanticFlow: A Self-Supervised Framework for Joint Scene Flow Prediction and Instance Segmentation in Dynamic Environments—0
ClimateGS: Real-Time Climate Simulation with 3D Gaussian Style Transfer—0
Incorporating Attributes and Multi-Scale Structures for Heterogeneous Graph Contrastive Learning—0
MTLoc: A Confidence-Based Source-Free Domain Adaptation Approach For Indoor Localization—0
PSA-SSL: Pose and Size-aware Self-Supervised Learning on LiDAR Point CloudsCode0
Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly DetectionCode0
Multi-Modal Self-Supervised Semantic Communication—0
RoMedFormer: A Rotary-Embedding Transformer Foundation Model for 3D Genito-Pelvic Structure Segmentation in MRI and CT—0
Text-Guided Image Invariant Feature Learning for Robust Image Watermarking—0
Towards Scalable Foundation Model for Multi-modal and Hyperspectral Geospatial Data—0
Learning from Synchronization: Self-Supervised Uncalibrated Multi-View Person Association in Challenging ScenesCode0
A Survey on Self-supervised Contrastive Learning for Multimodal Text-Image Analysis—0
Spherical Tree-Sliced Wasserstein DistanceCode0
RoMA: Scaling up Mamba-based Foundation Models for Remote SensingCode2
Transformers without NormalizationCode5
BioSerenity-E1: a self-supervised EEG model for medical applications—0
Bilingual Dual-Head Deep Model for Parkinson's Disease Detection from SpeechCode0
Evaluating Visual Explanations of Attention Maps for Transformer-based Medical Imaging—0
Degradation Self-Supervised Learning for Lithium-ion Battery Health DiagnosticsCode0
Is Limited Participant Diversity Impeding EEG-based Machine Learning?Code0
Open-World Skill Discovery from Unsegmented Demonstrations—0
Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?—0
Endo-FASt3r: Endoscopic Foundation model Adaptation for Structure from motion—0
MIRAM: Masked Image Reconstruction Across Multiple Scales for Breast Lesion Risk Prediction—0
Fully Unsupervised Annotation of C. Elegans—0
Divide and Conquer Self-Supervised Learning for High-Content Imaging—0
Temporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentation—0
PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization—0
TI-JEPA: An Innovative Energy-based Joint Embedding Strategy for Text-Image Multimodal Systems—0
Adversarial Robustness of Discriminative Self-Supervised Learning in Vision—0
STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal ClassificationCode1
Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning—0
Neural Descriptors: Self-Supervised Learning of Robust Local Surface Descriptors Using Polynomial PatchesCode0
Beyond H&E: Unlocking Pathological Insights with Polarization via Self-supervised Learning—0
Unsupervised Waste Classification By Dual-Encoder Contrastive Learning and Multi-Clustering Voting (DECMCV)—0
Leveraging Self-Supervised Learning Methods for Remote Screening of Subjects with Paroxysmal Atrial Fibrillation—0
Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training—0
A dataset-free approach for self-supervised learning of 3D reflectional symmetries—0
Open-source framework for detecting bias and overfitting for large pathology imagesCode0
EasyCraft: A Robust and Efficient Framework for Automatic Avatar Crafting—0
Lossy Neural Compression for Geospatial Analytics: A Review—0
Random Walks in Self-supervised Learning for Triangular Meshes—0
Show:102550
← PrevPage 6 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