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 1751–1800 of 5044 papers

TitleStatusHype
Self-supervision meets kernel graph neural models: From architecture to augmentations—0
Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity PriorCode1
Refining Latent Representations: A Generative SSL Approach for Heterogeneous Graph Learning—0
DORec: Decomposed Object Reconstruction and Segmentation Utilizing 2D Self-Supervised Features—0
Spatial HuBERT: Self-supervised Spatial Speech Representation Learning for a Single Talker from Multi-channel Audio—0
Multi Self-supervised Pre-fine-tuned Transformer Fusion for Better Intelligent Transportation Detection—0
PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image DenoisingCode1
Self-Supervised Models of Speech Infer Universal Articulatory Kinematics—0
SD-HuBERT: Sentence-Level Self-Distillation Induces Syllabic Organization in HuBERTCode1
Longitudinal Self-supervised Learning Using Neural Ordinary Differential Equation—0
Evading Detection Actively: Toward Anti-Forensics against Forgery Localization—0
An Empirical Study of Self-supervised Learning with Wasserstein Distance—0
MERTech: Instrument Playing Technique Detection Using Self-Supervised Pretrained Model With Multi-Task FinetuningCode0
Estimating Uncertainty in Multimodal Foundation Models using Public Internet DataCode0
STORM: Efficient Stochastic Transformer based World Models for Reinforcement LearningCode1
Contrastive Self-Supervised Learning for Spatio-Temporal Analysis of Lung Ultrasound Videos—0
SelfVC: Voice Conversion With Iterative Refinement using Self Transformations—0
SIDE: Self-supervised Intermediate Domain Exploration for Source-free Domain AdaptationCode0
Self supervised convolutional kernel based handcrafted feature harmonization: Enhanced left ventricle hypertension disease phenotyping on echocardiography—0
Incorporating Domain Knowledge Graph into Multimodal Movie Genre Classification with Self-Supervised Attention and Contrastive LearningCode0
Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video—0
Self-supervised visual learning for analyzing firearms trafficking activities on the Web—0
UniPAD: A Universal Pre-training Paradigm for Autonomous DrivingCode2
Fast Word Error Rate Estimation Using Self-Supervised Representations for Speech and Text—0
PU-Ray: Domain-Independent Point Cloud Upsampling via Ray Marching on Neural Implicit SurfaceCode0
DualAug: Exploiting Additional Heavy Augmentation with OOD Data RejectionCode0
Visual Self-supervised Learning Scheme for Dense Prediction Tasks on X-ray Images—0
CrIBo: Self-Supervised Learning via Cross-Image Object-Level BootstrappingCode1
Heuristic Vision Pre-Training with Self-Supervised and Supervised Multi-Task Learning—0
Enhancing expressivity transfer in textless speech-to-speech translation—0
Causal Unsupervised Semantic SegmentationCode1
Does resistance to style-transfer equal Global Shape Bias? Measuring network sensitivity to global shape configurationCode0
A Discrepancy Aware Framework for Robust Anomaly DetectionCode1
Computational Pathology at Health System Scale -- Self-Supervised Foundation Models from Three Billion Images—0
Antenna Response Consistency Driven Self-supervised Learning for WIFI-based Human Activity Recognition—0
Self-Supervised Representation Learning for Online Handwriting Text Classification—0
Self-Supervised Dataset Distillation for Transfer LearningCode1
Pain Forecasting using Self-supervised Learning and Patient Phenotyping: An attempt to prevent Opioid Addiction—0
USTEP: Spatio-Temporal Predictive Learning under A Unified View—0
Empower Nested Boolean Logic via Self-Supervised Curriculum LearningCode0
SimPLR: A Simple and Plain Transformer for Scaling-Efficient Object Detection and Segmentation—0
GestSync: Determining who is speaking without a talking headCode1
Enhancing Representations through Heterogeneous Self-Supervised Learning—0
A Comparative Study of Voice Conversion Models with Large-Scale Speech and Singing Data: The T13 Systems for the Singing Voice Conversion Challenge 2023—0
Score-based Diffusion Models With Self-supervised Learning For Accelerated 3D Multi-contrast Cardiac Magnetic Resonance Imaging—0
Do self-supervised speech and language models extract similar representations as human brain?—0
Unbiased and Robust: External Attention-enhanced Graph Contrastive Learning for Cross-domain Sequential RecommendationCode0
Federated Self-Supervised Learning of Monocular Depth Estimators for Autonomous Vehicles—0
AG-CRC: Anatomy-Guided Colorectal Cancer Segmentation in CT with Imperfect Anatomical KnowledgeCode0
MeSa: Masked, Geometric, and Supervised Pre-training for Monocular Depth Estimation—0
Show:102550
← PrevPage 36 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