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 1401–1450 of 5044 papers

TitleStatusHype
Multi-Modal Emotion Recognition by Text, Speech and Video Using Pretrained Transformers—0
Rethinking Graph Masked Autoencoders through Alignment and UniformityCode0
Two-Stage Multi-task Self-Supervised Learning for Medical Image Segmentation—0
Persian Speech Emotion Recognition by Fine-Tuning Transformers—0
Analysis of Self-Supervised Speech Models on Children's Speech and Infant Vocalizations—0
CochCeps-Augment: A Novel Self-Supervised Contrastive Learning Using Cochlear Cepstrum-based Masking for Speech Emotion RecognitionCode0
Low-Rank Approximation of Structural Redundancy for Self-Supervised LearningCode0
ExGRG: Explicitly-Generated Relation Graph for Self-Supervised Representation Learning—0
BarlowTwins-CXR : Enhancing Chest X-Ray abnormality localization in heterogeneous data with cross-domain self-supervised learning—0
TEE4EHR: Transformer Event Encoder for Better Representation Learning in Electronic Health RecordsCode0
Masked LoGoNet: Fast and Accurate 3D Image Analysis for Medical Domain—0
A self-supervised framework for learning whole slide representations—0
Task-customized Masked AutoEncoder via Mixture of Cluster-conditional Experts—0
VRMM: A Volumetric Relightable Morphable Head Model—0
Masked Graph Autoencoder with Non-discrete BandwidthsCode1
Online Feature Updates Improve Online (Generalized) Label Shift Adaptation—0
Positive and negative sampling strategies for self-supervised learning on audio-video dataCode0
Applying Unsupervised Semantic Segmentation to High-Resolution UAV Imagery for Enhanced Road Scene ParsingCode0
Dual Lagrangian Learning for Conic Optimization—0
Exploring Federated Self-Supervised Learning for General Purpose Audio Understanding—0
HASSOD: Hierarchical Adaptive Self-Supervised Object DetectionCode2
Stereographic Spherical Sliced Wasserstein DistancesCode0
Exploring Intrinsic Properties of Medical Images for Self-Supervised Binary Semantic Segmentation—0
Deep Spectral Improvement for Unsupervised Image Instance SegmentationCode0
Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of ElectrocardiogramCode2
Cooperative Knowledge Distillation: A Learner Agnostic ApproachCode0
SLYKLatent: A Learning Framework for Gaze Estimation Using Deep Facial Feature Learning—0
A Survey on Self-Supervised Learning for Non-Sequential Tabular DataCode3
KB-Plugin: A Plug-and-play Framework for Large Language Models to Induce Programs over Low-resourced Knowledge BasesCode0
Enhanced Urban Region Profiling with Adversarial Self-Supervised Learning for Robust Forecasting and Security—0
A Probabilistic Model Behind Self-Supervised LearningCode0
On the Transferability of Large-Scale Self-Supervision to Few-Shot Audio ClassificationCode1
Self-Supervised Contrastive Pre-Training for Multivariate Point Processes—0
VIS-MAE: An Efficient Self-supervised Learning Approach on Medical Image Segmentation and ClassificationCode0
Self-supervised learning of video representations from a child's perspectiveCode1
InfMAE: A Foundation Model in the Infrared ModalityCode2
How Useful is Continued Pre-Training for Generative Unsupervised Domain Adaptation?—0
What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis—0
Unveiling the Power of Self-supervision for Multi-view Multi-human Association and TrackingCode1
Adapting Amidst Degradation: Cross Domain Li-ion Battery Health Estimation via Physics-Guided Test-Time Training—0
M2CURL: Sample-Efficient Multimodal Reinforcement Learning via Self-Supervised Representation Learning for Robotic ManipulationCode1
ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf modelsCode3
Detection and Recovery Against Deep Neural Network Fault Injection Attacks Based on Contrastive Learning—0
Hybrid Transformer and Spatial-Temporal Self-Supervised Learning for Long-term Traffic Prediction—0
Depth Anything in Medical Images: A Comparative Study—0
Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote SensingCode2
MLEM: Generative and Contrastive Learning as Distinct Modalities for Event SequencesCode0
MV2MAE: Multi-View Video Masked Autoencoders—0
RecDCL: Dual Contrastive Learning for RecommendationCode1
MEA-Defender: A Robust Watermark against Model Extraction AttackCode1
Show:102550
← PrevPage 29 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