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 3751–3800 of 5044 papers

TitleStatusHype
Large vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learning—0
Analyzing Data-Centric Properties for Graph Contrastive LearningCode0
RAZE: Region Guided Self-Supervised Gaze Representation Learning—0
Underwater enhancement based on a self-learning strategy and attention mechanism for high-intensity regions—0
Deep Semi-Supervised and Self-Supervised Learning for Diabetic Retinopathy Detection—0
Multi-Feature Vision Transformer via Self-Supervised Representation Learning for Improvement of COVID-19 DiagnosisCode0
Automatically Discovering Novel Visual Categories with Self-supervised Prototype Learning—0
BYOLMed3D: Self-Supervised Representation Learning of Medical Videos using Gradient Accumulation Assisted 3D BYOL Framework—0
A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond—0
Improving Fine-tuning of Self-supervised Models with Contrastive InitializationCode0
RCA: Ride Comfort-Aware Visual Navigation via Self-Supervised Learning—0
HelixFold-Single: MSA-free Protein Structure Prediction by Using Protein Language Model as an Alternative—0
Towards Sleep Scoring Generalization Through Self-Supervised Meta-Learning—0
Deep Clustering with Features from Self-Supervised Pretraining—0
Time to augment self-supervised visual representation learning—0
Dynamic Channel Selection in Self-Supervised LearningCode0
Learning a Dual-Mode Speech Recognition Model via Self-Pruning—0
Explored An Effective Methodology for Fine-Grained Snake RecognitionCode0
Better Reasoning Behind Classification Predictions with BERT for Fake News Detection—0
Scale dependant layer for self-supervised nuclei encodingCode0
Contrastive Self-Supervised Learning Leads to Higher Adversarial Susceptibility—0
MetaComp: Learning to Adapt for Online Depth Completion—0
MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of BehaviorCode0
BYEL : Bootstrap Your Emotion LatentCode0
HyperNet: Self-Supervised Hyperspectral Spatial-Spectral Feature Understanding Network for Hyperspectral Change Detection—0
GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation LearningCode0
What Do We Maximize in Self-Supervised Learning?—0
End-to-End and Self-Supervised Learning for ComParE 2022 Stuttering Sub-Challenge—0
A-SFS: Semi-supervised Feature Selection based on Multi-task Self-supervision—0
ExAgt: Expert-guided Augmentation for Representation Learning of Traffic ScenariosCode0
Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action RecognitionCode0
Federated Self-Supervised Learning in Heterogeneous Settings: Limits of a Baseline Approach on HAR—0
Self-Supervised-RCNN for Medical Image Segmentation with Limited Data Annotation—0
TSPipe: Learn from Teacher Faster with PipelinesCode0
On the Importance of Hyperparameters and Data Augmentation for Self-Supervised Learning—0
Masked Spatial-Spectral Autoencoders Are Excellent Hyperspectral Defenders—0
Model-Aware Contrastive Learning: Towards Escaping the DilemmasCode0
SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection—0
Multi-Modal Unsupervised Pre-Training for Surgical Operating Room Workflow Analysis—0
HOME: High-Order Mixed-Moment-based Embedding for Representation Learning—0
Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models—0
Attribute Graphs Underlying Molecular Generative Models: Path to Learning with Limited Data—0
Unsupervised Hebbian Learning on Point Sets in StarCraft II—0
DSPNet: Towards Slimmable Pretrained Networks based on Discriminative Self-supervised Learning—0
Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learning—0
Patch-level instance-group discrimination with pretext-invariant learning for colitis scoring—0
Online Continual Learning of End-to-End Speech Recognition Models—0
Consistency is the key to further mitigating catastrophic forgetting in continual learningCode0
Self-supervised Learning with Local Contrastive Loss for Detection and Semantic Segmentation—0
Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain—0
Show:102550
← PrevPage 76 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