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 1851–1900 of 5044 papers

TitleStatusHype
Fine-Tuning Self-Supervised Learning Models for End-to-End Pronunciation ScoringCode1
Nebula: Self-Attention for Dynamic Malware AnalysisCode1
Realistic Website Fingerprinting By Augmenting Network TraceCode1
Scalable Label-efficient Footpath Network Generation Using Remote Sensing Data and Self-supervised LearningCode0
Self-supervised Multi-view Clustering in Computer Vision: A Survey—0
Non-Intrusive Speech Intelligibility Prediction for Hearing Aids using Whisper and Metadata—0
Self-supervised TransUNet for Ultrasound regional segmentation of the distal radius in children—0
RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopy—0
Improving Speech Inversion Through Self-Supervised Embeddings and Enhanced Tract Variables—0
Personalized Food Image Classification: Benchmark Datasets and New Baseline—0
Fine-tune the pretrained ATST model for sound event detectionCode1
Understanding the limitations of self-supervised learning for tabular anomaly detection—0
Hierarchical Metadata Information Constrained Self-Supervised Learning for Anomalous Sound Detection Under Domain Shift—0
Towards Universal Speech Discrete Tokens: A Case Study for ASR and TTS—0
Hodge-Aware Contrastive Learning—0
Virchow: A Million-Slide Digital Pathology Foundation ModelCode1
Learning Beyond Similarities: Incorporating Dissimilarities between Positive Pairs in Self-Supervised Time Series Learning—0
EnCodecMAE: Leveraging neural codecs for universal audio representation learningCode1
Enhancing Child Vocalization Classification with Phonetically-Tuned Embeddings for Assisting Autism Diagnosis—0
Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?Code1
GelFlow: Self-supervised Learning of Optical Flow for Vision-Based Tactile Sensor Displacement Measurement—0
Attention De-sparsification Matters: Inducing Diversity in Digital Pathology Representation Learning—0
Plasticity-Optimized Complementary Networks for Unsupervised Continual LearningCode0
Can large-scale vocoded spoofed data improve speech spoofing countermeasure with a self-supervised front end?—0
ssVERDICT: Self-Supervised VERDICT-MRI for Enhanced Prostate Tumour CharacterisationCode0
Adopting Self-Supervised Learning into Unsupervised Video Summarization through Restorative Score.Code1
Adopting Self-Supervised Learning into Unsupervised Video Summarization through Restorative ScoreCode1
Enhancing Hyperedge Prediction with Context-Aware Self-Supervised LearningCode0
Optimizing Audio Augmentations for Contrastive Learning of Health-Related Acoustic Signals—0
Decoupling Common and Unique Representations for Multimodal Self-supervised LearningCode1
Neural Koopman prior for data assimilationCode0
Graph-Aware Contrasting for Multivariate Time-Series ClassificationCode1
Towards Federated Learning Under Resource Constraints via Layer-wise Training and Depth Dropout—0
LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech—0
Continual Robot Learning using Self-Supervised Task Inference—0
Multi-view Self-supervised Disentanglement for General Image DenoisingCode1
Frequency-Aware Self-Supervised Long-Tailed Learning—0
Asymmetric Clean Segments-Guided Self-Supervised Learning for Robust Speaker Verification—0
Representation Synthesis by Probabilistic Many-Valued Logic Operation in Self-Supervised Learning—0
Overcoming Data Limitations: A Few-Shot Specific Emitter Identification Method Using Self-Supervised Learning and Adversarial AugmentationCode1
Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction—0
CDFSL-V: Cross-Domain Few-Shot Learning for VideosCode1
ETP: Learning Transferable ECG Representations via ECG-Text Pre-training—0
ViewMix: Augmentation for Robust Representation in Self-Supervised Learning—0
Towards Unsupervised Graph Completion Learning on Graphs with Features and Structure Missing—0
Stylebook: Content-Dependent Speaking Style Modeling for Any-to-Any Voice Conversion using Only Speech Data—0
Spatio-Temporal Contrastive Self-Supervised Learning for POI-level Crowd Flow Inference—0
Self-Supervised Masked Digital Elevation Models Encoding for Low-Resource Downstream Tasks—0
Non-Parametric Representation Learning with Kernels—0
Variational Self-Supervised Contrastive Learning Using Beta Divergence—0
Show:102550
← PrevPage 38 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