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 4051–4100 of 5044 papers

TitleStatusHype
How Well Do Self-Supervised Methods Perform in Cross-Domain Few-Shot Learning?—0
Masked prediction tasks: a parameter identifiability view—0
Survey on Self-supervised Representation Learning Using Image Transformations—0
Self-Supervised Representation Learning via Latent Graph Prediction—0
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision—0
Phase Aberration Robust Beamformer for Planewave US Using Self-Supervised Learning—0
Learning Contextually Fused Audio-visual Representations for Audio-visual Speech Recognition—0
Misinformation Detection in Social Media Video Posts—0
Synthetic Data Can Also Teach: Synthesizing Effective Data for Unsupervised Visual Representation Learning—0
Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learning—0
NeuroMixGDP: A Neural Collapse-Inspired Random Mixup for Private Data ReleaseCode0
A Generic Self-Supervised Framework of Learning Invariant Discriminative Features—0
Unlabeled Data Help: Minimax Analysis and Adversarial Robustness—0
AI can evolve without labels: self-evolving vision transformer for chest X-ray diagnosis through knowledge distillation—0
Classification of Microscopy Images of Breast Tissue: Region Duplication based Self-Supervision vs. Off-the Shelf Deep Representations—0
Reduced order modeling for flow and transport problems with Barlow Twins self-supervised learning—0
Investigating Power laws in Deep Representation Learning—0
Using Navigational Information to Learn Visual Representations—0
Results and findings of the 2021 Image Similarity Challenge—0
Self-supervised Contrastive Learning for Cross-domain Hyperspectral Image Representation—0
How to Understand Masked Autoencoders—0
Simple Control Baselines for Evaluating Transfer Learning—0
Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship AttributionCode0
Exemplar-Based Contrastive Self-Supervised Learning with Few-Shot Class Incremental Learning—0
Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Series—0
SubOmiEmbed: Self-supervised Representation Learning of Multi-omics Data for Cancer Type ClassificationCode0
Relative Position Prediction as Pre-training for Text Encoders—0
AtmoDist: Self-supervised Representation Learning for Atmospheric DynamicsCode0
Understanding The Robustness of Self-supervised Learning Through Topic Modeling—0
ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition—0
Learning Robust Representation through Graph Adversarial Contrastive Learning—0
Contrastive Learning from Demonstrations—0
Self Semi Supervised Neural Architecture Search for Semantic Segmentation—0
DSFormer: A Dual-domain Self-supervised Transformer for Accelerated Multi-contrast MRI Reconstruction—0
S2MS: Self-Supervised Learning Driven Multi-Spectral CT Image Enhancement—0
Link Prediction with Contextualized Self-Supervision—0
Consistent 3D Hand Reconstruction in Video via self-supervised Learning—0
Bi-CLKT: Bi-Graph Contrastive Learning based Knowledge Tracing—0
Enhancing Hyperbolic Graph Embeddings via Contrastive Learning—0
CELESTIAL: Classification Enabled via Labelless Embeddings with Self-supervised Telescope Image Analysis Learning—0
CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning—0
Learning Pixel Trajectories with Multiscale Contrastive Random Walks—0
TransFuse: A Unified Transformer-based Image Fusion Framework using Self-supervised Learning—0
Deep Cervix Model Development from Heterogeneous and Partially Labeled Image Datasets—0
Knowledge Distillation as Self-Supervised Learning—0
On The Effects of Learning Views on Neural Representations in Self-Supervised Learning—0
BERT vs ALBERT explained—0
CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data—0
Video Transformers: A Survey—0
SS-3DCapsNet: Self-supervised 3D Capsule Networks for Medical Segmentation on Less Labeled Data—0
Show:102550
← PrevPage 82 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