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 4551–4600 of 5044 papers

TitleStatusHype
Knowledge-aware Contrastive Molecular Graph Learning—0
Revisiting Self-Supervised Monocular Depth EstimationCode0
DIG: A Turnkey Library for Diving into Graph Deep Learning Research—0
Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations—0
Bootstrapped Self-Supervised Training with Monocular Video for Semantic Segmentation and Depth Estimation—0
Ano-Graph: Learning Normal Scene Contextual Graphs to Detect Video Anomalies—0
Dementia Severity Classification under Small Sample Size and Weak Supervision in Thick Slice MRI—0
Self-Supervised Learning of Audio Representations from Permutations with Differentiable Ranking—0
Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised LearningCode0
Distributed Linear-Quadratic Control with Graph Neural Networks—0
Self-Supervised Motion Retargeting with Safety Guarantee—0
Self-supervised Text-to-SQL Learning with Header Alignment Training—0
Cross-modal Image Retrieval with Deep Mutual Information Maximization—0
Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning—0
Multi-Pretext Attention Network for Few-shot Learning with Self-supervisionCode0
Self-supervised Regularization for Text Classification—0
Self-supervised SAR-optical Data Fusion and Land-cover Mapping using Sentinel-1/-2 Images—0
Wav2vec-C: A Self-supervised Model for Speech Representation Learning—0
Self-Supervision by Prediction for Object Discovery in Videos—0
Bootstrapped Representation Learning on Graphs—0
Imbalance-Aware Self-Supervised Learning for 3D Radiomic Representations—0
Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data? A Theoretical Analysis—0
Liver Fibrosis and NAS scoring from CT images using self-supervised learning and texture encodingCode0
Helicopter Track Identification with Autoencoder—0
Self-supervised Pretraining of Visual Features in the Wild—0
Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations—0
Contrastive Separative Coding for Self-supervised Representation Learning—0
ADAADepth: Adapting Data Augmentation and Attention for Self-Supervised Monocular Depth Estimation—0
A Brief Summary of Interactions Between Meta-Learning and Self-Supervised Learning—0
Towards Continual, Online, Self-Supervised DepthCode0
Domain Adapting Ability of Self-Supervised Learning for Face Recognition—0
Towards Robust Graph Contrastive Learning—0
Enabling the Network to Surf the Internet—0
"Train one, Classify one, Teach one" -- Cross-surgery transfer learning for surgical step recognition—0
Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptation—0
Self-Supervised Learning of Graph Neural Networks: A Unified Review—0
UPRec: User-Aware Pre-training for Recommender Systems—0
Contrastive Self-supervised Neural Architecture SearchCode0
Self-Supervised Learning via multi-Transformation Classification for Action Recognition—0
An Empirical Study on Measuring the Similarity of Sentential Arguments with Language Model Domain Adaptation—0
Large-Context Conversational Representation Learning: Self-Supervised Learning for Conversational Documents—0
MAPGN: MAsked Pointer-Generator Network for sequence-to-sequence pre-training—0
Adversarial defense for automatic speaker verification by cascaded self-supervised learning models—0
Self-Supervised Multisensor Change Detection—0
Self-supervised learning for fast and scalable time series hyper-parameter tuning—0
Improving Scene Graph Classification by Exploiting Knowledge from Texts—0
Conversational Query Rewriting with Self-supervised Learning—0
A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learning—0
Custom Object Detection via Multi-Camera Self-Supervised Learning—0
Multi-Task Self-Supervised Pre-Training for Music Classification—0
Show:102550
← PrevPage 92 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