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 3251–3300 of 5044 papers

TitleStatusHype
Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised LearningCode2
Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data—0
Variable-rate hierarchical CPC leads to acoustic unit discovery in speechCode1
Poisson2Sparse: Self-Supervised Poisson Denoising From a Single ImageCode1
MSR: Making Self-supervised learning Robust to Aggressive Augmentations—0
On the duality between contrastive and non-contrastive self-supervised learning—0
Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group DiscriminationCode1
Toward a realistic model of speech processing in the brain with self-supervised learning—0
KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property PredictionCode1
Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods—0
Self-supervised Learning of Audio Representations from Audio-Visual Data using Spatial Alignment—0
Hyperspherical Consistency RegularizationCode1
Understanding the Role of Nonlinearity in Training Dynamics of Contrastive Learning—0
Siamese Image Modeling for Self-Supervised Vision Representation LearningCode1
Impact Analysis of the Use of Speech and Language Models Pretrained by Self-Supersivion for Spoken Language Understanding—0
Augmentation Component Analysis: Modeling Similarity via the Augmentation OverlapsCode0
Self-supervised Learning for Label Sparsity in Computational Drug Repositioning—0
Where are my Neighbors? Exploiting Patches Relations in Self-Supervised Vision TransformerCode1
Efficient Self-supervised Vision Pretraining with Local Masked ReconstructionCode1
Generalized Supervised Contrastive Learning—0
Self-Supervised Learning as a Means To Reduce the Need for Labeled Data in Medical Image AnalysisCode0
3D Graph Contrastive Learning for Molecular Property Prediction—0
COIN: Co-Cluster Infomax for Bipartite Graphs—0
Self-Supervised Learning for Building Damage Assessment from Large-scale xBD Satellite Imagery Benchmark DatasetsCode0
Pseudo-Data based Self-Supervised Federated Learning for Classification of Histopathological Images—0
Analysis of Augmentations for Contrastive ECG Representation Learning—0
StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech SynthesisCode2
Self-Supervised Visual Representation Learning with Semantic GroupingCode1
MetaSSD: Meta-Learned Self-Supervised DetectionCode1
GMML is All you NeedCode1
Conformal Credal Self-Supervised LearningCode0
Is Lip Region-of-Interest Sufficient for Lipreading?—0
Data Generation for Satellite Image Classification Using Self-Supervised Representation Learning—0
A Closer Look at Self-Supervised Lightweight Vision TransformersCode1
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingCode2
Architecture-Agnostic Masked Image Modeling -- From ViT back to CNNCode4
Semantic-aware Dense Representation Learning for Remote Sensing Image Change DetectionCode1
Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature DistillationCode2
Raising the Bar in Graph-level Anomaly DetectionCode1
Task-Customized Self-Supervised Pre-training with Scalable Dynamic Routing—0
Cross-Architecture Self-supervised Video Representation LearningCode1
HIRL: A General Framework for Hierarchical Image Representation LearningCode1
Triangular Contrastive Learning on Molecular Graphs—0
Contrastive Learning with Boosted MemorizationCode1
Federated Self-supervised Learning for Heterogeneous Clients—0
Additive Logistic Mechanism for Privacy-Preserving Self-Supervised Learning—0
Low-rank Optimal Transport: Approximation, Statistics and Debiasing—0
SCVRL: Shuffled Contrastive Video Representation Learning—0
Multi-Augmentation for Efficient Visual Representation Learning for Self-supervised Pre-trainingCode0
Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods—0
Show:102550
← PrevPage 66 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