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 1801–1850 of 5044 papers

TitleStatusHype
Non-Neighbors Also Matter to Kriging: A New Contrastive-Prototypical LearningCode0
CLAWSAT: Towards Both Robust and Accurate Code ModelsCode0
ExAgt: Expert-guided Augmentation for Representation Learning of Traffic ScenariosCode0
Hierarchical Context Learning of object components for unsupervised semantic segmentationCode0
Noisier2Inverse: Self-Supervised Learning for Image Reconstruction with Correlated NoiseCode0
Noise-Robust Keyword Spotting through Self-supervised PretrainingCode0
NoisyActions2M: A Multimedia Dataset for Video Understanding from Noisy LabelsCode0
Novel Class Discovery: an Introduction and Key ConceptsCode0
Classification of Breast Cancer Histopathology Images using a Modified Supervised Contrastive Learning MethodCode0
Cooperative Knowledge Distillation: A Learner Agnostic ApproachCode0
Node Feature Extraction by Self-Supervised Multi-scale Neighborhood PredictionCode0
Neural Identification for ControlCode0
Neural Koopman prior for data assimilationCode0
EVA-X: A Foundation Model for General Chest X-ray Analysis with Self-supervised LearningCode0
Evaluation of self-supervised pre-training for automatic infant movement classification using wearable movement sensorsCode0
PhiNet v2: A Mask-Free Brain-Inspired Vision Foundation Model from VideoCode0
Neural Descriptors: Self-Supervised Learning of Robust Local Surface Descriptors Using Polynomial PatchesCode0
Evaluating Variants of wav2vec 2.0 on Affective Vocal Burst TasksCode0
CLANet: A Comprehensive Framework for Cross-Batch Cell Line Identification Using Brightfield ImagesCode0
Neural Blind Deconvolution Using Deep PriorsCode0
NeuroMixGDP: A Neural Collapse-Inspired Random Mixup for Private Data ReleaseCode0
Histopathology DatasetGAN: Synthesizing Large-Resolution Histopathology DatasetsCode0
Privacy-Preserving Models for Legal Natural Language ProcessingCode0
Evaluating Self-supervised Speech Models on a Taiwanese Hokkien CorpusCode0
A Self-supervised Learning System for Object Detection in Videos Using Random Walks on GraphsCode0
Circumventing Backdoor Space via Weight SymmetryCode0
NearbyPatchCL: Leveraging Nearby Patches for Self-Supervised Patch-Level Multi-Class Classification in Whole-Slide ImagesCode0
Circuit Design and Efficient Simulation of Quantum Inner Product and Empirical Studies of Its Effect on Near-Term Hybrid Quantum-Classic Machine LearningCode0
NarrowBERT: Accelerating Masked Language Model Pretraining and InferenceCode0
A Self-supervised Learning System for Object Detection using Physics Simulation and Multi-view Pose EstimationCode0
Choice of training label matters: how to best use deep learning for quantitative MRI parameter estimationCode0
Estimating Uncertainty in Multimodal Foundation Models using Public Internet DataCode0
MVEB: Self-Supervised Learning with Multi-View Entropy BottleneckCode0
Establishing Deep InfoMax as an effective self-supervised learning methodology in materials informaticsCode0
MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillationCode0
Multi-Temporal Relationship Inference in Urban AreasCode0
Multi-View Graph Representation Learning Beyond HomophilyCode0
Erasing Self-Supervised Learning Backdoor by Cluster Activation MaskingCode0
Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few LabelsCode0
Multispectral Contrastive Learning with Viewmaker NetworksCode0
Multi-Pretext Attention Network for Few-shot Learning with Self-supervisionCode0
EquiMod: An Equivariance Module to Improve Self-Supervised LearningCode0
EqCo: Equivalent Rules for Self-supervised Contrastive LearningCode0
A Self-Supervised Learning Approach to Rapid Path Planning for Car-Like Vehicles Maneuvering in Urban EnvironmentCode0
Multi-view self-supervised learning for multivariate variable-channel time seriesCode0
Cervical Optical Coherence Tomography Image Classification Based on Contrastive Self-Supervised Texture LearningCode0
Multi-modal Masked Siamese Network Improves Chest X-Ray Representation LearningCode0
CERT: Contrastive Self-supervised Learning for Language UnderstandingCode0
Adversarial Skill Networks: Unsupervised Robot Skill Learning from VideoCode0
Multi-Modal Perception Attention Network with Self-Supervised Learning for Audio-Visual Speaker TrackingCode0
Show:102550
← PrevPage 37 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