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 2601–2650 of 5044 papers

TitleStatusHype
Exploring Self-Supervised Representation Ensembles for COVID-19 Cough Classification—0
Exploring Siamese Networks in Self-Supervised Fast MRI Reconstruction—0
Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study—0
Exploring SSL Discrete Tokens for Multilingual ASR—0
Exploring StyleGAN Latent Space for Face Alignment with Limited Training Data—0
Exploring Temporal Granularity in Self-Supervised Video Representation Learning—0
Exploring the Common Principal Subspace of Deep Features in Neural Networks—0
Exploring the Diversity and Invariance in Yourself for Visual Pre-Training Task—0
Exploring the Impact of Data Quantity on ASR in Extremely Low-resource Languages—0
Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation—0
Exploring the Potential of SSL Models for Sound Event Detection—0
Exploring the Task-agnostic Trait of Self-supervised Learning in the Context of Detecting Mental Disorders—0
Exploring Visual Pre-training for Robot Manipulation: Datasets, Models and Methods—0
Exploring WavLM on Speech Enhancement—0
Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods—0
Extending Momentum Contrast with Cross Similarity Consistency Regularization—0
Generalized 3D Self-supervised Learning Framework via Prompted Foreground-Aware Feature Contrast—0
FaceGPT: Self-supervised Learning to Chat about 3D Human Faces—0
Failure-Proof Non-Contrastive Self-Supervised Learning—0
Fair Foundation Models for Medical Image Analysis: Challenges and Perspectives—0
Fast Adaptation for Human Pose Estimation via Meta-Optimization—0
Fast and Robust Face-to-Parameter Translation for Game Character Auto-Creation—0
FastGCL: Fast Self-Supervised Learning on Graphs via Contrastive Neighborhood Aggregation—0
FastInject: Injecting Unpaired Text Data into CTC-based ASR training—0
Fast Traversability Estimation for Wild Visual Navigation—0
Fast Word Error Rate Estimation Using Self-Supervised Representations for Speech and Text—0
FaultSeg Swin-UNETR: Transformer-Based Self-Supervised Pretraining Model for Fault Recognition—0
FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition—0
Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models—0
Feature Alignment by Uncertainty and Self-Training for Source-Free Unsupervised Domain Adaptation—0
Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning—0
Feature diversity in self-supervised learning—0
Feature Learning in Image Hierarchies using Functional Maximal Correlation—0
Feature Normalization for Fine-tuning Self-Supervised Models in Speech Enhancement—0
Feature Representation Learning with Adaptive Displacement Generation and Transformer Fusion for Micro-Expression Recognition—0
Federated Alternate Training (FAT): Leveraging Unannotated Data Silos in Federated Segmentation for Medical Imaging—0
Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learning—0
Federated Contrastive Learning for Volumetric Medical Image Segmentation—0
Federated Contrastive Representation Learning with Feature Fusion and Neighborhood Matching—0
Federated Cycling (FedCy): Semi-supervised Federated Learning of Surgical Phases—0
Federated Learning for Face Recognition via Intra-subject Self-supervised Learning—0
Federated Learning without Full Labels: A Survey—0
Federated Momentum Contrastive Clustering—0
Federated Representation Learning for Automatic Speech Recognition—0
Federated Self-Supervised Contrastive Learning and Masked Autoencoder for Dermatological Disease Diagnosis—0
Federated Self-supervised Domain Generalization for Label-efficient Polyp Segmentation—0
Federated Self-Supervised Learning for Acoustic Event Classification—0
Federated Self-supervised Learning for Heterogeneous Clients—0
Federated Self-Supervised Learning for One-Shot Cross-Modal and Cross-Imaging Technique Segmentation—0
Federated Self-Supervised Learning in Heterogeneous Settings: Limits of a Baseline Approach on HAR—0
Show:102550
← PrevPage 53 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