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

Showing 40514100 of 5044 papers

TitleStatusHype
DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD classification directly from H&E whole-slide images in colorectal and breast cancerCode0
Bridging the Gap between Language Model and Reading Comprehension: Unsupervised MRC via Self-Supervision0
Compound Figure Separation of Biomedical Images with Side LossCode0
Reasoning-Modulated Representations0
Unsupervised Skill-Discovery and Skill-Learning in Minecraft0
CCVS: Context-aware Controllable Video SynthesisCode1
Self-supervised Representation Learning Framework for Remote Physiological Measurement Using Spatiotemporal Augmentation LossCode1
Exploiting generative self-supervised learning for the assessment of biological images with lack of annotations: a COVID-19 case-study0
CLSRIL-23: Cross Lingual Speech Representations for Indic LanguagesCode1
Exploiting Image Translations via Ensemble Self-Supervised Learning for Unsupervised Domain Adaptation0
Kit-Net: Self-Supervised Learning to Kit Novel 3D Objects into Novel 3D CavitiesCode0
eProduct: A Million-Scale Visual Search Benchmark to Address Product Recognition ChallengesCode1
Clustering-Based Representation Learning through Output Translation and Its Application to Remote--Sensing ImagesCode0
End-to-end Multi-modal Video Temporal GroundingCode1
UniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset0
Deep Fiber Clustering: Anatomically Informed Unsupervised Deep Learning for Fast and Effective White Matter Parcellation0
Hierarchical Self-Supervised Learning for Medical Image Segmentation Based on Multi-Domain Data Aggregation0
Layer-wise Analysis of a Self-supervised Speech Representation ModelCode1
Dropout Regularization for Self-Supervised Learning of Transformer Encoder Speech Representation0
Improved Language Identification Through Cross-Lingual Self-Supervised Learning0
Investigate the Essence of Long-Tailed Recognition from a Unified PerspectiveCode0
SelfCF: A Simple Framework for Self-supervised Collaborative FilteringCode1
InfoNCE is variational inference in a recognition parameterised model0
Multi-Level Graph Contrastive Learning0
Continual Contrastive Learning for Image ClassificationCode0
Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning0
Learning a Model for Inferring a Spatial Road Lane Network Graph using Self-SupervisionCode1
Bag of Instances Aggregation Boosts Self-supervised DistillationCode1
Hybrid Supervision Learning for Pathology Whole Slide Image ClassificationCode1
Pretext Tasks selection for multitask self-supervised speech representation learningCode0
Leveraging Hidden Structure in Self-Supervised Learning0
Two-Stage Self-Supervised Cycle-Consistency Network for Reconstruction of Thin-Slice MR Images0
AutoNovel: Automatically Discovering and Learning Novel Visual CategoriesCode1
As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learningCode0
Understanding Cognitive Fatigue from fMRI Scans with Self-supervised Learning0
LiteGEM: Lite Geometry Enhanced Molecular Representation Learning for Quantum Property Prediction0
Intent Disentanglement and Feature Self-supervision for Novel Recommendation0
Co^2L: Contrastive Continual LearningCode1
Time-Series Representation Learning via Temporal and Contextual ContrastingCode1
Intrinsically Motivated Self-supervised Learning in Reinforcement Learning0
Domain-Specific Pretraining for Vertical Search: Case Study on Biomedical Literature0
Self-Supervised Monocular Depth Estimation of Untextured Indoor Rotated ScenesCode1
Conditional Deformable Image Registration with Convolutional Neural NetworkCode1
Bootstrap Representation Learning for Segmentation on Medical Volumes and Sequences0
Improving Transformer-based Sequential Recommenders through Preference Editing0
STRESS: Super-Resolution for Dynamic Fetal MRI using Self-Supervised LearningCode1
Learning from Pseudo Lesion: A Self-supervised Framework for COVID-19 Diagnosis0
Credal Self-Supervised LearningCode0
Unsupervised Object-Level Representation Learning from Scene ImagesCode1
NCIS: Neural Contextual Iterative Smoothing for Purifying Adversarial Perturbations0
Show:102550
← PrevPage 82 of 101Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Pretraining: NoneImages & Text57.5Unverified
2Pretraining: ShEDImages & Text54.3Unverified
3Pretraining: e-MixImages & Text48.9Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50Accuracy91.7Unverified
2ResNet18Accuracy91.02Unverified
3MV-MRAccuracy89.67Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy93.89Unverified
2ResNet18average top-1 classification accuracy92.58Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy72.51Unverified
2ResNet18average top-1 classification accuracy69.31Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet50)Top-1 Accuracy82.64Unverified
2CorInfomax (ResNet18)Top-1 Accuracy80.48Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy51.84Unverified
2ResNet18average top-1 classification accuracy51.67Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet18)Top-1 Accuracy93.18Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet18)Top-1 Accuracy71.61Unverified
#ModelMetricClaimedVerifiedStatus
1Hybrid BYOL-S/CvTAccuracy67.2Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet50)Top-1 Accuracy54.86Unverified