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 551–600 of 5044 papers

TitleStatusHype
Can bidirectional encoder become the ultimate winner for downstream applications of foundation models?—0
k2SSL: A Faster and Better Framework for Self-Supervised Speech Representation Learning—0
New Test-Time Scenario for Biosignal: Concept and Its Approach—0
SatVision-TOA: A Geospatial Foundation Model for Coarse-Resolution All-Sky Remote Sensing ImageryCode1
Contrastive Graph Condensation: Advancing Data Versatility through Self-Supervised Learning—0
Self-supervised Video Instance Segmentation Can Boost Geographic Entity Alignment in Historical Maps—0
Abnormality-Driven Representation Learning for Radiology Imaging—0
Learning 3D Representations from Procedural 3D Programs—0
ZoomLDM: Latent Diffusion Model for multi-scale image generationCode1
Probing the Mid-level Vision Capabilities of Self-Supervised Learning—0
Machine Learning for the Digital Typhoon Dataset: Extensions to Multiple Basins and New Developments in Representations and TasksCode1
DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders—0
High-Resolution Be Aware! Improving the Self-Supervised Real-World Super-Resolution—0
Low-Data Classification of Historical Music Manuscripts: A Few-Shot Learning Approach—0
SKQVC: One-Shot Voice Conversion by K-Means Quantization with Self-Supervised Speech Representations—0
Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization—0
Multi-Token Enhancing for Vision Representation Learning—0
J-Invariant Volume Shuffle for Self-Supervised Cryo-Electron Tomogram Denoising on Single Noisy Volume—0
Unsupervised Machine Learning for Osteoporosis Diagnosis Using Singh Index Clustering on Hip Radiographs—0
Self-Supervised Learning for Ordered Three-Dimensional Structures—0
Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models—0
Self-supervised learning for radio-astronomy source classification: a benchmarkCode0
BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term DetectionCode0
Unleashing the Power of Large Language Models for Group POI Recommendations—0
Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction—0
Unsupervised Foundation Model-Agnostic Slide-Level Representation LearningCode1
Residual Vision Transformer (ResViT) Based Self-Supervised Learning Model for Brain Tumor Classification—0
Self-Supervised Learning in Deep Networks: A Pathway to Robust Few-Shot Classification—0
GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous DrivingCode2
KDC-MAE: Knowledge Distilled Contrastive Mask Auto-Encoder—0
Physics-Guided Detector for SAR AirplanesCode1
In-Situ Melt Pool Characterization via Thermal Imaging for Defect Detection in Directed Energy Deposition Using Vision Transformers—0
Multi-Modal Self-Supervised Learning for Surgical Feedback Effectiveness AssessmentCode0
Infinite Width Limits of Self Supervised Neural Networks—0
LLaSA: Large Language and Structured Data Assistant—0
From Prototypes to General Distributions: An Efficient Curriculum for Masked Image Modeling—0
STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing—0
Self-Supervised Learning of Grasping Arbitrary Objects On-the-Move—0
XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack DetectionCode1
Building 6G Radio Foundation Models with Transformer Architectures—0
PFML: Self-Supervised Learning of Time-Series Data Without Representation CollapseCode0
Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos—0
Self-Supervised Radio Pre-training: Toward Foundational Models for Spectrogram Learning—0
Partial Multi-View Clustering via Meta-Learning and Contrastive Feature Alignment—0
Assessing the Performance of the DINOv2 Self-supervised Learning Vision Transformer Model for the Segmentation of the Left Atrium from MRI Images—0
Masked Image Modeling Boosting Semi-Supervised Semantic SegmentationCode0
3-DUSSS: 3-Dimensional Ultrasonic Self Supervised Segmentation—0
DINO-LG: A Task-Specific DINO Model for Coronary Calcium Scoring—0
SynStitch: a Self-Supervised Learning Network for Ultrasound Image Stitching Using Synthetic Training Pairs and Indirect Supervision—0
Variational Graph Contrastive LearningCode0
Show:102550
← PrevPage 12 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