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 851–900 of 5044 papers

TitleStatusHype
Whitening Consistently Improves Self-Supervised LearningCode0
Masked Image Modeling: A SurveyCode1
Temporal Variability and Multi-Viewed Self-Supervised Representations to Tackle the ASVspoof5 Deepfake Challenge—0
Heterogeneous Space Fusion and Dual-Dimension Attention: A New Paradigm for Speech Enhancement—0
BSS-CFFMA: Cross-Domain Feature Fusion and Multi-Attention Speech Enhancement Network based on Self-Supervised EmbeddingCode0
Membership Inference Attack Against Masked Image Modeling—0
SMILES-Mamba: Chemical Mamba Foundation Models for Drug ADMET Prediction—0
HySparK: Hybrid Sparse Masking for Large Scale Medical Image Pre-TrainingCode1
Efficient Test-Time Prompt Tuning for Vision-Language Models—0
PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-IdentificationCode1
Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised LearningCode0
scASDC: Attention Enhanced Structural Deep Clustering for Single-cell RNA-seq DataCode1
Detection of Animal Movement from Weather Radar using Self-Supervised Learning—0
AggSS: An Aggregated Self-Supervised Approach for Class-Incremental Learning—0
Dual-branch PolSAR Image Classification Based on GraphMAE and Local Feature Extraction—0
CoBooM: Codebook Guided Bootstrapping for Medical Image Representation Learning—0
Non-Causal to Causal SSL-Supported Transfer Learning: Towards a High-Performance Low-Latency Speech Vocoder—0
AI Foundation Models in Remote Sensing: A Survey—0
Training on the Fly: On-device Self-supervised Learning aboard Nano-drones within 20 mW—0
Diffusion Model Meets Non-Exemplar Class-Incremental Learning and Beyond—0
Self-Supervised Learning for Multi-Channel Neural Transducer—0
Multistain Pretraining for Slide Representation Learning in PathologyCode2
Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility EstimationCode2
Past Movements-Guided Motion Representation Learning for Human Motion PredictionCode0
Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers—0
Embodiment: Self-Supervised Depth Estimation Based on Camera Models—0
Rethinking Pre-Trained Feature Extractor Selection in Multiple Instance Learning for Whole Slide Image ClassificationCode0
Contrastive Learning with Adaptive Neighborhoods for Brain Age Prediction on 3D Stiffness Maps—0
How Effective are Self-Supervised Models for Contact Identification in Videos—0
EXAONEPath 1.0 Patch-level Foundation Model for PathologyCode1
Mobility-Aware Federated Self-supervised Learning in Vehicular Network—0
Advancing Medical Image Segmentation: Morphology-Driven Learning with Diffusion TransformerCode0
Dense Self-Supervised Learning for Medical Image Segmentation—0
Enhancing CTR Prediction through Sequential Recommendation Pre-training: Introducing the SRP4CTR Framework—0
Fusion Self-supervised Learning for Recommendation—0
Self-Supervised Learning for Text Recognition: A Critical Survey—0
ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks—0
Revisit Event Generation Model: Self-Supervised Learning of Event-to-Video Reconstruction with Implicit Neural Representations—0
Self-supervised pre-training with diffusion model for few-shot landmark detection in x-ray images—0
Exploring the Effect of Dataset Diversity in Self-Supervised Learning for Surgical Computer VisionCode2
A Large Encoder-Decoder Family of Foundation Models For Chemical LanguageCode0
Unsqueeze [CLS] Bottleneck to Learn Rich RepresentationsCode0
Contrastive Learning Is Not Optimal for Quasiperiodic Time Series—0
PiPa++: Towards Unification of Domain Adaptive Semantic Segmentation via Self-supervised Learning—0
Automatic Equalization for Individual Instrument Tracks Using Convolutional Neural Networks—0
Federated Learning for Face Recognition via Intra-subject Self-supervised Learning—0
A Comprehensive Survey of LLM Alignment Techniques: RLHF, RLAIF, PPO, DPO and More—0
Predicting the Best of N Visual TrackersCode1
Overview of Speaker Modeling and Its Applications: From the Lens of Deep Speaker Representation Learning—0
MedMAE: A Self-Supervised Backbone for Medical Imaging TasksCode0
Show:102550
← PrevPage 18 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