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

Showing 15511600 of 5044 papers

TitleStatusHype
Self-supervised Learning for Enhancing Geometrical Modeling in 3D-Aware Generative Adversarial Network0
DMT: Comprehensive Distillation with Multiple Self-supervised Teachers0
Scale-Equivariant Imaging: Self-Supervised Learning for Image Super-Resolution and DeblurringCode1
Collaborative Learning for Annotation-Efficient Volumetric MR Image Segmentation0
Efficiency-oriented approaches for self-supervised speech representation learning0
CEIR: Concept-based Explainable Image Representation Learning0
Harnessing small projectors and multiple views for efficient vision pretrainingCode1
CONCSS: Contrastive-based Context Comprehension for Dialogue-appropriate Prosody in Conversational Speech Synthesis0
SELM: Speech Enhancement Using Discrete Tokens and Language Models0
Test-Time Domain Adaptation by Learning Domain-Aware Batch NormalizationCode0
SeiT++: Masked Token Modeling Improves Storage-efficient TrainingCode1
T-MAE: Temporal Masked Autoencoders for Point Cloud Representation LearningCode0
A novel dual-stream time-frequency contrastive pretext tasks framework for sleep stage classificationCode0
Self-Supervised Learning for Anomalous Sound DetectionCode1
PathoDuet: Foundation Models for Pathological Slide Analysis of H&E and IHC StainsCode2
CNC-Net: Self-Supervised Learning for CNC Machining Operations0
Deep Anomaly Detection in Text0
FastInject: Injecting Unpaired Text Data into CTC-based ASR training0
Audio-visual fine-tuning of audio-only ASR models0
Guided Diffusion from Self-Supervised Diffusion Features0
STaR: Distilling Speech Temporal Relation for Lightweight Speech Self-Supervised Learning ModelsCode1
Towards Model-Based Data Acquisition for Subjective Multi-Task NLP ProblemsCode0
Novel View Synthesis with View-Dependent Effects from a Single Image0
Erasing Self-Supervised Learning Backdoor by Cluster Activation MaskingCode0
PAD: Self-Supervised Pre-Training with Patchwise-Scale Adapter for Infrared ImagesCode1
Contextually Affinitive Neighborhood Refinery for Deep ClusteringCode1
Building Universal Foundation Models for Medical Image Analysis with Spatially Adaptive NetworksCode1
Learned representation-guided diffusion models for large-image generationCode1
NearbyPatchCL: Leveraging Nearby Patches for Self-Supervised Patch-Level Multi-Class Classification in Whole-Slide ImagesCode0
Multimodal Pretraining of Medical Time Series and NotesCode1
Optimizing Likelihood-free Inference using Self-supervised Neural Symmetry EmbeddingsCode0
Medical Vision Language Pretraining: A survey0
Jumpstarting Surgical Computer Vision0
GAMC: An Unsupervised Method for Fake News Detection using Graph Autoencoder with MaskingCode1
Non-Cartesian Self-Supervised Physics-Driven Deep Learning Reconstruction for Highly-Accelerated Multi-Echo Spiral fMRI0
The Counterattack of CNNs in Self-Supervised Learning: Larger Kernel Size might be All You Need0
Prospective Role of Foundation Models in Advancing Autonomous Vehicles0
Data Scarcity in Recommendation Systems: A Survey0
A Review of Machine Learning Methods Applied to Video Analysis Systems0
An Experimental Study: Assessing the Combined Framework of WavLM and BEST-RQ for Text-to-Speech Synthesis0
Cross-BERT for Point Cloud Pretraining0
Large-scale Training of Foundation Models for Wearable Biosignals0
Neural Spectral Methods: Self-supervised learning in the spectral domainCode1
VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment0
Series2Vec: Similarity-based Self-supervised Representation Learning for Time Series ClassificationCode1
TimeDRL: Disentangled Representation Learning for Multivariate Time-SeriesCode1
Bootstrapping Autonomous Driving Radars with Self-Supervised LearningCode1
Evaluating Self-supervised Speech Models on a Taiwanese Hokkien CorpusCode0
Bootstrap Your Own Variance0
DiffPMAE: Diffusion Masked Autoencoders for Point Cloud ReconstructionCode1
Show:102550
← PrevPage 32 of 101Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Pretraining: NoneImages & Text57.5Unverified
2Pretraining: ShEDImages & Text54.3Unverified
3Pretraining: e-MixImages & Text48.9Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50Accuracy91.7Unverified
2ResNet18Accuracy91.02Unverified
3MV-MRAccuracy89.67Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy93.89Unverified
2ResNet18average top-1 classification accuracy92.58Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy72.51Unverified
2ResNet18average top-1 classification accuracy69.31Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet50)Top-1 Accuracy82.64Unverified
2CorInfomax (ResNet18)Top-1 Accuracy80.48Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy51.84Unverified
2ResNet18average top-1 classification accuracy51.67Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet18)Top-1 Accuracy93.18Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet18)Top-1 Accuracy71.61Unverified
#ModelMetricClaimedVerifiedStatus
1Hybrid BYOL-S/CvTAccuracy67.2Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet50)Top-1 Accuracy54.86Unverified