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 2751–2800 of 5044 papers

TitleStatusHype
Pretraining ECG Data with Adversarial Masking Improves Model Generalizability for Data-Scarce TasksCode0
AgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridging—0
Homomorphic Self-Supervised Learning—0
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive LearningCode1
Improving Children's Speech Recognition by Fine-tuning Self-supervised Adult Speech RepresentationsCode0
Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning—0
Information-guided pixel augmentation for pixel-wise contrastive learning—0
MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple TargetsCode1
Stain-invariant self supervised learning for histopathology image analysisCode1
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic SegmentationCode1
Learning from partially labeled data for multi-organ and tumor segmentationCode1
SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth ObservationCode2
LLEDA -- Lifelong Self-Supervised Domain Adaptation—0
Intent-aware Multi-source Contrastive Alignment for Tag-enhanced Recommendation—0
An Adapter based Multi-label Pre-training for Speech Separation and Enhancement—0
A Survey of Knowledge Enhanced Pre-trained Language Models—0
The Far Side of Failure: Investigating the Impact of Speech Recognition Errors on Subsequent Dementia ClassificationCode0
3D-CSL: self-supervised 3D context similarity learning for Near-Duplicate Video RetrievalCode1
Self-supervised learning with bi-label masked speech prediction for streaming multi-talker speech recognition—0
Self-supervised learning of audio representations using angular contrastive lossCode0
Contrastive Self-Supervised Learning for Skeleton Representations—0
Flaky Performances when Pretraining on Relational Databases—0
Speech separation with large-scale self-supervised learning—0
Interactive Feature Embedding for Infrared and Visible Image Fusion—0
miCSE: Mutual Information Contrastive Learning for Low-shot Sentence EmbeddingsCode1
Pushing the limits of self-supervised speaker verification using regularized distillation framework—0
On Web-based Visual Corpus Construction for Visual Document UnderstandingCode1
On minimal variations for unsupervised representation learning—0
Generalizable Re-Identification from Videos with Cycle Association—0
ProtoX: Explaining a Reinforcement Learning Agent via PrototypingCode0
Understanding the properties and limitations of contrastive learning for Out-of-Distribution detection—0
Local Manifold Augmentation for Multiview Semantic Consistency—0
Privacy-Preserving Models for Legal Natural Language ProcessingCode0
Self-Supervised Learning for Speech Enhancement through SynthesisCode0
Biased Self-supervised learning for ASR—0
Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech ProcessingCode1
MAST: Multiscale Audio Spectrogram TransformersCode1
Beyond Instance Discrimination: Relation-aware Contrastive Self-supervised LearningCode0
SLICER: Learning universal audio representations using low-resource self-supervised pre-trainingCode1
More Speaking or More Speakers?—0
data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setupCode1
EquiMod: An Equivariance Module to Improve Self-Supervised LearningCode0
RegCLR: A Self-Supervised Framework for Tabular Representation Learning in the Wild—0
How Well Do Unsupervised Learning Algorithms Model Human Real-time and Life-long Learning?Code0
Rethinking Low-level Features for Interest Point Detection and DescriptionCode1
Avoid Overthinking in Self-Supervised Models for Speech Recognition—0
Self-supervised Character-to-Character Distillation for Text RecognitionCode1
Self-Supervised Learning with Limited Labeled Data for Prostate Cancer Detection in High Frequency Ultrasound—0
RGMIM: Region-Guided Masked Image Modeling for Learning Meaningful Representations from X-Ray Images—0
Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features—0
Show:102550
← PrevPage 56 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