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 4451–4500 of 5044 papers

TitleStatusHype
K-PLUG: KNOWLEDGE-INJECTED PRE-TRAINED LANGUAGE MODEL FOR NATURAL LANGUAGE UNDERSTANDING AND GENERATIONCode1
Contrastive Self-Supervised Learning of Global-Local Audio-Visual Representations—0
Online Adversarial Purification based on Self-supervised Learning—0
Erasure for Advancing: Dynamic Self-Supervised Learning for Commonsense Reasoning—0
A Theory of Self-Supervised Framework for Few-Shot Learning—0
Shuffle to Learn: Self-supervised learning from permutations via differentiable ranking—0
Run Away From your Teacher: a New Self-Supervised Approach Solving the Puzzle of BYOL—0
Self-supervised Adversarial Robustness for the Low-label, High-data Regime—0
ECONET: Effective Continual Pretraining of Language Models for Event Temporal ReasoningCode1
Hybrid Interest Modeling for Long-tailed Users—0
From Handheld to Unconstrained Object Detection: a Weakly-supervised On-line Learning Approach—0
Self-Supervised Multimodal Domino: in Search of Biomarkers for Alzheimer's DiseaseCode0
Self-Supervised Representation Learning for Astronomical ImagesCode1
Adversarial Momentum-Contrastive Pre-TrainingCode0
Motif-Driven Contrastive Learning of Graph Representations—0
Self-supervised self-supervision by combining deep learning and probabilistic logic—0
Self-Supervised Learning for Visual Summary Identification in Scientific Publications—0
OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised LearningCode1
Self-supervised monocular depth estimation from oblique UAV videosCode0
Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks—0
Self-supervised Learning with Fully Convolutional Networks—0
Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-TrainingCode1
Overcoming Language Priors with Self-supervised Learning for Visual Question AnsweringCode1
The effectiveness of unsupervised subword modeling with autoregressive and cross-lingual phone-aware networks—0
ISD: Self-Supervised Learning by Iterative Similarity DistillationCode1
Self-Supervised Sketch-to-Image SynthesisCode1
CODE: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert LinkingCode1
Aggregative Self-Supervised Feature Learning from a Limited Sample—0
HR-Depth: High Resolution Self-Supervised Monocular Depth EstimationCode1
Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling TransferCode1
InferCode: Self-Supervised Learning of Code Representations by Predicting Subtrees—0
Self-Supervised Hypergraph Convolutional Networks for Session-based RecommendationCode1
Exploiting Behavioral Consistence for Universal User Representation—0
Context Matters: Graph-based Self-supervised Representation Learning for Medical ImagesCode1
Debiased-CAM to mitigate image perturbations with faithful visual explanations of machine learning—0
Self-Supervised Learning of Lidar Segmentation for Autonomous Indoor NavigationCode1
Concept Generalization in Visual Representation LearningCode1
Contrastive Transformation for Self-supervised Correspondence LearningCode1
CASTing Your Model: Learning to Localize Improves Self-Supervised Representations—0
Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology—0
Temporal-Aware Self-Supervised Learning for 3D Hand Pose and Mesh Estimation in Videos—0
Art Style Classification with Self-Trained Ensemble of AutoEncoding Transformations—0
Pre-training Protein Language Models with Label-Agnostic Binding Pairs Enhances Performance in Downstream TasksCode1
Is It a Plausible Colour? UCapsNet for Image ColourisationCode0
Rethinking supervised learning: insights from biological learning and from calling it by its name—0
SAM: Self-supervised Learning of Pixel-wise Anatomical Embeddings in Radiological ImagesCode1
Super-Selfish: Self-Supervised Learning on Images with PyTorchCode1
Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning—0
Co-mining: Self-Supervised Learning for Sparsely Annotated Object DetectionCode1
Cross-Loss Influence Functions to Explain Deep Network RepresentationsCode0
Show:102550
← PrevPage 90 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