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 501–550 of 5044 papers

TitleStatusHype
Wearable Accelerometer Foundation Models for Health via Knowledge Distillation—0
Dynamic Entity-Masked Graph Diffusion Model for histopathological image Representation LearningCode0
Motor Imagery Classification for Asynchronous EEG-Based Brain-Computer InterfacesCode0
Deep Learning Model Security: Threats and Defenses—0
DomCLP: Domain-wise Contrastive Learning with Prototype Mixup for Unsupervised Domain GeneralizationCode0
A Unified Model For Voice and Accent Conversion In Speech and Singing using Self-Supervised Learning and Feature Extraction—0
Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill LearningCode1
Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning?Code0
Spatio-temporal Latent Representations for the Analysis of Acoustic Scenes in-the-wild—0
EvRepSL: Event-Stream Representation via Self-Supervised Learning for Event-Based VisionCode1
Diagnosis and Severity Assessment of Ulcerative Colitis using Self Supervised Learning—0
Visual Lexicon: Rich Image Features in Language Space—0
On-Device Self-Supervised Learning of Low-Latency Monocular Depth from Only Events—0
Pruning All-Rounder: Rethinking and Improving Inference Efficiency for Large Vision Language Models—0
Self-supervised cost of transport estimation for multimodal path planning—0
Self-Supervised Learning with Probabilistic Density Labeling for Rainfall Probability EstimationCode0
CardOOD: Robust Query-driven Cardinality Estimation under Out-of-Distribution—0
Osteoporosis Prediction from Hand X-ray Images Using Segmentation-for-Classification and Self-Supervised Learning—0
Mitigating Instance-Dependent Label Noise: Integrating Self-Supervised Pretraining with Pseudo-Label Refinement—0
Unsupervised Hyperspectral and Multispectral Image Fusion via Self-Supervised Modality DecouplingCode0
Birth and Death of a Rose—0
Learning Symmetry-Independent Jet Representations via Jet-Based Joint Embedding Predictive Architecture—0
Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian NoiseCode4
Transferring self-supervised pre-trained models for SHM data anomaly detection with scarce labeled data—0
CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing—0
Training MLPs on Graphs without SupervisionCode1
Analytic Study of Text-Free Speech Synthesis for Raw Audio using a Self-Supervised Learning Model—0
Equivariant Representation Learning for Augmentation-based Self-Supervised Learning via Image Reconstruction—0
Beyond [cls]: Exploring the true potential of Masked Image Modeling representationsCode1
MAGMA: Manifold Regularization for MAEsCode0
GUESS: Generative Uncertainty Ensemble for Self Supervision—0
Rethinking Self-Supervised Learning Within the Framework of Partial Information Decomposition—0
GenMix: Effective Data Augmentation with Generative Diffusion Model Image Editing—0
Direct Coloring for Self-Supervised Enhanced Feature Decoupling—0
Self-Supervised Learning-Based Path Planning and Obstacle Avoidance Using PPO and B-Splines in Unknown Environments—0
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-trainingCode1
R.I.P.: A Simple Black-box Attack on Continual Test-time Adaptation—0
Gen-SIS: Generative Self-augmentation Improves Self-supervised Learning—0
Beyond Pairwise Correlations: Higher-Order Redundancies in Self-Supervised Representation Learning—0
Explorations in Self-Supervised Learning: Dataset Composition Testing for Object Classification—0
Enhancing the Generalization Capability of Skin Lesion Classification Models with Active Domain Adaptation Methods—0
Rethinking Generalizability and Discriminability of Self-Supervised Learning from Evolutionary Game Theory PerspectiveCode0
Noro: A Noise-Robust One-shot Voice Conversion System with Hidden Speaker Representation Capabilities—0
Multimodal Whole Slide Foundation Model for PathologyCode4
Demographic Predictability in 3D CT Foundation EmbeddingsCode0
CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image CollectionsCode1
Point Cloud Unsupervised Pre-training via 3D Gaussian Splatting—0
Perturbation Ontology based Graph Attention Networks—0
Can bidirectional encoder become the ultimate winner for downstream applications of foundation models?—0
RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable DataCode1
Show:102550
← PrevPage 11 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