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 4301–4350 of 5044 papers

TitleStatusHype
Federated Contrastive Representation Learning with Feature Fusion and Neighborhood Matching—0
Data-Efficient Contrastive Learning by Differentiable Hard Sample and Hard Positive Pair Generation—0
AAVAE: Augmentation-Augmented Variational Autoencoders—0
Sphere2Vec: Self-Supervised Location Representation Learning on Spherical Surfaces—0
Residual Contrastive Learning: Unsupervised Representation Learning from Residuals—0
Understanding Self-supervised Learning via Information Bottleneck Principle—0
Rethinking Temperature in Graph Contrastive LearningCode0
Chaos is a Ladder: A New Understanding of Contrastive Learning—0
ESCo: Towards Provably Effective and Scalable Contrastive Representation Learning—0
Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations—0
3D Pre-training improves GNNs for Molecular Property Prediction—0
Environment Predictive Coding for Visual Navigation—0
Ensembles and Encoders for Task-Free Continual Learning—0
Self-GenomeNet: Self-supervised Learning with Reverse-Complement Context Prediction for Nucleotide-level Genomics Data—0
Learning Minimal Representations with Model Invariance—0
Encoding Event-Based Gesture Data With a Hybrid SNN Guided Variational Auto-encoder—0
A theoretically grounded characterization of feature representations—0
Lifting Imbalanced Regression with Self-Supervised Learning—0
LEARNING PHONEME-LEVEL DISCRETE SPEECH REPRESENTATION WITH WORD-LEVEL SUPERVISION—0
Towards Better Understanding and Better Generalization of Low-shot Classification in Histology Images with Contrastive Learning—0
Self-Supervised Learning for 3D Medical Image Analysis using 3D SimCLR and Monte Carlo Dropout—0
Self-supervised Learning for Sequential Recommendation with Model Augmentation—0
Learning Universal User Representations via Self-Supervised Lifelong Behaviors Modeling—0
Learning Background Invariance Improves Generalization and Robustness in Self-Supervised Learning on ImageNet and Beyond—0
How Well Does Self-Supervised Pre-Training Perform with Streaming ImageNet?—0
The Tensor Brain: A Unified Theory of Perception, Memory and Semantic DecodingCode0
Multi-source Few-shot Domain Adaptation—0
Self-supervised Learning for Semi-supervised Temporal Language Grounding—0
Multi-view Contrastive Self-Supervised Learning of Accounting Data Representations for Downstream Audit Tasks—0
How much human-like visual experience do current self-supervised learning algorithms need in order to achieve human-level object recognition?Code0
Self-Supervised Learning to Prove Equivalence Between Straight-Line Programs via Rewrite RulesCode0
DialogueBERT: A Self-Supervised Learning based Dialogue Pre-training Encoder—0
Socially Supervised Representation Learning: the Role of Subjectivity in Learning Efficient Representations—0
A Study of the Generalizability of Self-Supervised Representations—0
Interest-oriented Universal User Representation via Contrastive Learning—0
Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signals—0
Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer—0
Unsupervised View-Invariant Human Posture Representation—0
Self-Supervised Neural Architecture Search for Imbalanced DatasetsCode0
Improving Streaming Transformer Based ASR Under a Framework of Self-supervised Learning—0
Deep Bregman Divergence for Contrastive Learning of Visual Representations—0
The potential of self-supervised networks for random noise suppression in seismic data—0
Improving Accent Identification and Accented Speech Recognition Under a Framework of Self-supervised Learning—0
Self-Supervised Metric Learning With Graph Clustering For Speaker DiarizationCode0
Robust Inverse Framework using Knowledge-guided Self-Supervised Learning: An application to Hydrology—0
Online Unsupervised Learning of Visual Representations and CategoriesCode0
Self supervised learning improves dMMR/MSI detection from histology slides across multiple cancers—0
WeakSTIL: Weak whole-slide image level stromal tumor infiltrating lymphocyte scores are all you need—0
On the Sins of Image Synthesis Loss for Self-supervised Depth Estimation—0
Attention-based Contrastive Learning for Winograd SchemasCode0
Show:102550
← PrevPage 87 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