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 2201–2250 of 5044 papers

TitleStatusHype
Siamese Transformer Networks for Few-shot Image Classification—0
A Closer Look at Benchmarking Self-Supervised Pre-training with Image Classification—0
Universal Sound Separation with Self-Supervised Audio Masked Autoencoder—0
An efficient framework based on large foundation model for cervical cytopathology whole slide image screeningCode0
Efficient Unsupervised Visual Representation Learning with Explicit Cluster BalancingCode0
DINO Pre-training for Vision-based End-to-end Autonomous Driving—0
Joint-Embedding Predictive Architecture for Self-Supervised Learning of Mask Classification Architecture—0
A Self-Supervised Learning Pipeline for Demographically Fair Facial Attribute Classification—0
Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape DataCode0
On the Role of Discrete Tokenization in Visual Representation LearningCode0
Tissue-Contrastive Semi-Masked Autoencoders for Segmentation Pretraining on Chest CT—0
Bootstrapping Vision-language Models for Self-supervised Remote Physiological Measurement—0
Robust and Explainable Framework to Address Data Scarcity in Diagnostic Imaging—0
Self-supervised visual learning from interactions with objectsCode0
TE-SSL: Time and Event-aware Self Supervised Learning for Alzheimer's Disease Progression AnalysisCode0
A Clinical Benchmark of Public Self-Supervised Pathology Foundation ModelsCode0
Analyzing Speech Unit Selection for Textless Speech-to-Speech Translation—0
MSP-Podcast SER Challenge 2024: L'antenne du Ventoux Multimodal Self-Supervised Learning for Speech Emotion Recognition—0
Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised LearningCode0
Leveraging image captions for selective whole slide image annotationCode0
LaFAM: Unsupervised Feature Attribution with Label-free Activation MapsCode0
Transfer or Self-Supervised? Bridging the Performance Gap in Medical Imaging—0
Test-time adaptation for geospatial point cloud semantic segmentation with distinct domain shifts—0
Self-supervised Learning via Cluster Distance Prediction for Operating Room Context Awareness—0
Performance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian Dialect—0
Multi-modal Masked Siamese Network Improves Chest X-Ray Representation LearningCode0
Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis—0
Heterogeneous Hypergraph Embedding for Recommendation SystemsCode0
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks—0
Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition—0
Precision at Scale: Domain-Specific Datasets On-DemandCode0
LLMcap: Large Language Model for Unsupervised PCAP Failure Detection—0
SA-WavLM: Speaker-Aware Self-Supervised Pre-training for Mixture Speech—0
A Spatio-Temporal Representation Learning as an Alternative to Traditional Glosses in Sign Language Translation and Production—0
Learning from Memory: Non-Parametric Memory Augmented Self-Supervised Learning of Visual FeaturesCode0
The USTC-NERCSLIP Systems for The ICMC-ASR Challenge—0
Towards the Next Frontier in Speech Representation Learning Using Disentanglement—0
Learning Paradigms and Modelling Methodologies for Digital Twins in Process Industry—0
ToCoAD: Two-Stage Contrastive Learning for Industrial Anomaly Detection—0
Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked PretrainingCode0
Towards Robust Speech Representation Learning for Thousands of Languages—0
SAFE: a SAR Feature Extractor based on self-supervised learning and masked Siamese ViTsCode0
Establishing Deep InfoMax as an effective self-supervised learning methodology in materials informaticsCode0
Assistive Image Annotation Systems with Deep Learning and Natural Language Capabilities: A Review—0
Multi-modal Food Recommendation using Clustering and Self-supervised Learning—0
Shorter SPECT Scans Using Self-supervised Coordinate Learning to Synthesize Skipped Projection Views—0
Mixture of Experts in a Mixture of RL settings—0
WV-Net: A foundation model for SAR WV-mode satellite imagery trained using contrastive self-supervised learning on 10 million imagesCode0
Foundation Models for ECG: Leveraging Hybrid Self-Supervised Learning for Advanced Cardiac Diagnostics—0
Speaker-Independent Acoustic-to-Articulatory Inversion through Multi-Channel Attention DiscriminatorCode0
Show:102550
← PrevPage 45 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