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 101–150 of 5044 papers

TitleStatusHype
Investigating Fine- and Coarse-grained Structural Correspondences Between Deep Neural Networks and Human Object Image Similarity Judgments Using Unsupervised Alignment—0
On the Out-of-Distribution Generalization of Self-Supervised LearningCode0
Mitigating Overfitting in Medical Imaging: Self-Supervised Pretraining vs. ImageNet Transfer Learning for Dermatological Diagnosis—0
Layer-wise Investigation of Large-Scale Self-Supervised Music Representation Models—0
An Inclusive Foundation Model for Generalizable Cytogenetics in Precision Oncology—0
Lung Nodule-SSM: Self-Supervised Lung Nodule Detection and Classification in Thoracic CT ImagesCode0
The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text DetectionCode1
VET-DINO: Learning Anatomical Understanding Through Multi-View Distillation in Veterinary Imaging—0
Detection of Underwater Multi-Targets Based on Self-Supervised Learning and Deformable Path Aggregation Feature Pyramid Network—0
Stronger ViTs With Octic EquivarianceCode1
Beginning with You: Perceptual-Initialization Improves Vision-Language Representation and Alignment—0
Physics-Driven Local-Whole Elastic Deformation Modeling for Point Cloud Representation Learning—0
SSPS: Self-Supervised Positive Sampling for Robust Self-Supervised Speaker VerificationCode0
Self-Supervised Learning for Image Segmentation: A Comprehensive Survey—0
3D Gaussian Adaptive Reconstruction for Fourier Light-Field Microscopy—0
Informed Mixing -- Improving Open Set Recognition via Attribution-based Augmentation—0
Graph Alignment for Benchmarking Graph Neural Networks and Learning Positional Encodings—0
AdaDim: Dimensionality Adaptation for SSL Representational Dynamics—0
Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning—0
Spectral-Spatial Self-Supervised Learning for Few-Shot Hyperspectral Image ClassificationCode1
PRETI: Patient-Aware Retinal Foundation Model via Metadata-Guided Representation LearningCode0
Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data CurriculumCode0
Exploring the Potential of SSL Models for Sound Event Detection—0
Spatiotemporal Field Generation Based on Hybrid Mamba-Transformer with Physics-informed Fine-tuning—0
Toward Adaptive Categories: Dimensional Governance for Agentic AI—0
Fractal Graph Contrastive Learning—0
Maximizing Asynchronicity in Event-based Neural Networks—0
PhiNet v2: A Mask-Free Brain-Inspired Vision Foundation Model from VideoCode0
Physics-informed Temporal Alignment for Auto-regressive PDE Foundation ModelsCode1
GAIA: A Foundation Model for Operational Atmospheric Dynamics—0
Large Wireless Localization Model (LWLM): A Foundation Model for Positioning in 6G NetworksCode1
A Unified and Scalable Membership Inference Method for Visual Self-supervised Encoder via Part-aware CapabilityCode0
A Multi-Task Foundation Model for Wireless Channel Representation Using Contrastive and Masked Autoencoder Learning—0
Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image AnalysisCode7
BioVFM-21M: Benchmarking and Scaling Self-Supervised Vision Foundation Models for Biomedical Image AnalysisCode0
Investigating self-supervised features for expressive, multilingual voice conversion—0
Thoughts on Objectives of Sparse and Hierarchical Masked Image Model—0
Generalizable Pancreas Segmentation via a Dual Self-Supervised Learning Framework—0
Deep Learning Advances in Vision-Based Traffic Accident Anticipation: A Comprehensive Review of Methods,Datasets,and Future Directions—0
Image Classification Using a Diffusion Model as a Pre-Training Model—0
Joint Low-level and High-level Textual Representation Learning with Multiple Masking Strategies—0
TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning ModelsCode1
SimMIL: A Universal Weakly Supervised Pre-Training Framework for Multi-Instance Learning in Whole Slide Pathology Images—0
Physics-informed Temporal Difference Metric Learning for Robot Motion PlanningCode1
Towards a Unified Representation Evaluation Framework Beyond Downstream TasksCode0
Hybrid Learning: A Novel Combination of Self-Supervised and Supervised Learning for MRI Reconstruction without High-Quality Training Reference—0
Score-based Self-supervised MRI Denoising—0
Benchmarking Ophthalmology Foundation Models for Clinically Significant Age Macular Degeneration Detection—0
UniCO: Towards a Unified Model for Combinatorial Optimization Problems—0
Learning based convex approximation for constrained parametric optimization—0
Show:102550
← PrevPage 3 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