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 551–600 of 5044 papers

TitleStatusHype
Decoupling Common and Unique Representations for Multimodal Self-supervised LearningCode1
Deep Self-Supervised Representation Learning for Free-Hand SketchCode1
Deciphering and integrating invariants for neural operator learning with various physical mechanismsCode1
Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural FieldsCode1
Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial RobustnessCode1
Deep Unfolded Tensor Robust PCA with Self-supervised LearningCode1
Self-supervised Learning from a Multi-view PerspectiveCode1
DATA: Domain-Aware and Task-Aware Self-supervised LearningCode1
Data Augmentation for Object Detection via Differentiable Neural RenderingCode1
Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the LeastCode1
DailyMAE: Towards Pretraining Masked Autoencoders in One DayCode1
D2C: Diffusion-Denoising Models for Few-shot Conditional GenerationCode1
DAS-N2N: Machine learning Distributed Acoustic Sensing (DAS) signal denoising without clean dataCode1
Data-Efficient Reinforcement Learning with Self-Predictive RepresentationsCode1
CutPaste: Self-Supervised Learning for Anomaly Detection and LocalizationCode1
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual RepresentationsCode1
CUTS: A Deep Learning and Topological Framework for Multigranular Unsupervised Medical Image SegmentationCode1
Anomaly Detection Requires Better RepresentationsCode1
Boosting Contrastive Self-Supervised Learning with False Negative CancellationCode1
Anomaly Detection on Attributed Networks via Contrastive Self-Supervised LearningCode1
Adopting Self-Supervised Learning into Unsupervised Video Summarization through Restorative Score.Code1
CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World DomainsCode1
CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from ImageCode1
Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical ImagingCode1
An Embarrassingly Simple Backdoor Attack on Self-supervised LearningCode1
Extending global-local view alignment for self-supervised learning with remote sensing imageryCode1
Cross-Architecture Self-supervised Video Representation LearningCode1
Anomaly Detection in Video via Self-Supervised and Multi-Task LearningCode1
3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised LearningCode1
CAiD: Context-Aware Instance Discrimination for Self-supervised Learning in Medical ImagingCode1
Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain AdaptationCode1
Boosting Generalization in Bio-Signal Classification by Learning the Phase-Amplitude CouplingCode1
Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill LearningCode1
D2C: Diffusion-Decoding Models for Few-Shot Conditional GenerationCode1
Boosting Self-Supervised Embeddings for Speech EnhancementCode1
DABS: A Domain-Agnostic Benchmark for Self-Supervised LearningCode1
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and LanguageCode1
data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setupCode1
A Note on Connecting Barlow Twins with Negative-Sample-Free Contrastive LearningCode1
Data-Centric Learning from Unlabeled Graphs with Diffusion ModelCode1
Large-Scale Representation Learning on Graphs via BootstrappingCode1
A clinically motivated self-supervised approach for content-based image retrieval of CT liver imagesCode1
Adopting Self-Supervised Learning into Unsupervised Video Summarization through Restorative ScoreCode1
Bootstrapping Autonomous Driving Radars with Self-Supervised LearningCode1
Blockwise Self-Supervised Learning at ScaleCode1
Decoupled Contrastive LearningCode1
Deeper into Self-Supervised Monocular Indoor Depth EstimationCode1
Bootstrap your own latent: A new approach to self-supervised LearningCode1
Bootstrap Your Own Latent - A New Approach to Self-Supervised LearningCode1
Cross-Architectural Positive Pairs improve the effectiveness of Self-Supervised LearningCode1
Show:102550
← PrevPage 12 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