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 1251–1300 of 5044 papers

TitleStatusHype
ViTAR: Vision Transformer with Any Resolution—0
Noise-Robust Keyword Spotting through Self-supervised PretrainingCode0
Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning—0
Efficient Image Pre-Training with Siamese Cropped Masked AutoencodersCode2
Masked Autoencoders are PDE LearnersCode0
Boosting Few-Shot Learning with Disentangled Self-Supervised Learning and Meta-Learning for Medical Image Classification—0
Self-STORM: Deep Unrolled Self-Supervised Learning for Super-Resolution MicroscopyCode0
Dyna-LfLH: Learning Agile Navigation in Dynamic Environments from Learned Hallucination—0
Self-Supervised Learning for Medical Image Data with Anatomy-Oriented Imaging Planes—0
Towards Large-Scale Training of Pathology Foundation ModelsCode2
A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based PerspectiveCode1
Connecting the Dots: Inferring Patent Phrase Similarity with Retrieved Phrase Graphs—0
Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark DiscoveryCode0
One Masked Model is All You Need for Sensor Fault Detection, Isolation and Accommodation—0
L-MAE: Longitudinal masked auto-encoder with time and severity-aware encoding for diabetic retinopathy progression prediction—0
Boarding for ISS: Imbalanced Self-Supervised: Discovery of a Scaled Autoencoder for Mixed Tabular Datasets—0
Technical Report: Masked Skeleton Sequence Modeling for Learning Larval Zebrafish Behavior Latent Embeddings—0
Towards Adversarial Robustness And Backdoor Mitigation in SSLCode0
Leave No One Behind: Online Self-Supervised Self-Distillation for Sequential RecommendationCode0
Exploring the Task-agnostic Trait of Self-supervised Learning in the Context of Detecting Mental Disorders—0
Pose-Aware Self-Supervised Learning with Viewpoint Trajectory RegularizationCode0
Point-DETR3D: Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection—0
Self-Supervised Backbone Framework for Diverse Agricultural Vision Tasks—0
Application of Tensorized Neural Networks for Cloud Classification—0
AdaProj: Adaptively Scaled Angular Margin Subspace Projections for Anomalous Sound Detection with Auxiliary Classification TasksCode0
Exploring Green AI for Audio Deepfake DetectionCode0
Hierarchical Text-to-Vision Self Supervised Alignment for Improved Histopathology Representation LearningCode1
MTP: Advancing Remote Sensing Foundation Model via Multi-Task PretrainingCode3
On Pretraining Data Diversity for Self-Supervised LearningCode1
Emotic Masked Autoencoder with Attention Fusion for Facial Expression Recognition—0
Quantifying uncertainty in lung cancer segmentation with foundation models applied to mixed-domain datasets—0
Learning Cross-view Visual Geo-localization without Ground Truth—0
Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEsCode2
Federated Semi-supervised Learning for Medical Image Segmentation with intra-client and inter-client Consistency—0
Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose EstimationCode1
Low-Trace Adaptation of Zero-shot Self-supervised Blind Image Denoising—0
IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature RepresentationCode0
Unsupervised End-to-End Training with a Self-Defined TargetCode0
Learning Useful Representations of Recurrent Neural Network Weight MatricesCode0
S-JEPA: towards seamless cross-dataset transfer through dynamic spatial attentionCode1
GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised LearningCode1
MLVICX: Multi-Level Variance-Covariance Exploration for Chest X-ray Self-Supervised Representation Learning—0
A Versatile Framework for Multi-scene Person Re-identificationCode2
SQ-LLaVA: Self-Questioning for Large Vision-Language AssistantCode1
Securely Fine-tuning Pre-trained Encoders Against Adversarial ExamplesCode1
Repoformer: Selective Retrieval for Repository-Level Code Completion—0
BirdSet: A Large-Scale Dataset for Audio Classification in Avian BioacousticsCode2
Self-Supervised Learning for Time Series: Contrastive or Generative?Code1
Anomaly Detection by Adapting a pre-trained Vision Language Model—0
Data-Efficient Sleep Staging with Synthetic Time Series PretrainingCode0
Show:102550
← PrevPage 26 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