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 651700 of 5044 papers

TitleStatusHype
Self-supervised Learning from a Multi-view PerspectiveCode1
ECONET: Effective Continual Pretraining of Language Models for Event Temporal ReasoningCode1
Co-mining: Self-Supervised Learning for Sparsely Annotated Object DetectionCode1
ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot LearningCode1
Adversarial Masking for Self-Supervised LearningCode1
CoLES: Contrastive Learning for Event Sequences with Self-SupervisionCode1
CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World DomainsCode1
Evidence of Vocal Tract Articulation in Self-Supervised Learning of SpeechCode1
3D Object Detection with a Self-supervised Lidar Scene Flow BackboneCode1
Exploit Clues from Views: Self-Supervised and Regularized Learning for Multiview Object RecognitionCode1
A Review on Self-Supervised Learning for Time Series Anomaly Detection: Recent Advances and Open ChallengesCode1
CASS: Cross Architectural Self-Supervision for Medical Image AnalysisCode1
Exploring Masked Autoencoders for Sensor-Agnostic Image Retrieval in Remote SensingCode1
Exploring Stochastic Autoregressive Image Modeling for Visual RepresentationCode1
Deep Unfolded Tensor Robust PCA with Self-supervised LearningCode1
Defending Against Patch-based Backdoor Attacks on Self-Supervised LearningCode1
Deep learning powered real-time identification of insects using citizen science dataCode1
Exploring The Role of Mean Teachers in Self-supervised Masked Auto-EncodersCode1
Exponential Moving Average Normalization for Self-supervised and Semi-supervised LearningCode1
Causal Unsupervised Semantic SegmentationCode1
Comprehensive Layer-wise Analysis of SSL Models for Audio Deepfake DetectionCode1
FCCDN: Feature Constraint Network for VHR Image Change DetectionCode1
CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representationsCode1
CCGL: Contrastive Cascade Graph LearningCode1
A Self-Correcting Sequential RecommenderCode1
CCVS: Context-aware Controllable Video SynthesisCode1
CDFSL-V: Cross-Domain Few-Shot Learning for VideosCode1
FedMed-ATL: Misaligned Unpaired Brain Image Synthesis via Affine Transform LossCode1
Concept Generalization in Visual Representation LearningCode1
Fine-tune the pretrained ATST model for sound event detectionCode1
FireRisk: A Remote Sensing Dataset for Fire Risk Assessment with Benchmarks Using Supervised and Self-supervised LearningCode1
FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised LearningCode1
A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-IdentificationCode1
A Discrepancy Aware Framework for Robust Anomaly DetectionCode1
Fragment-based Pretraining and Finetuning on Molecular GraphsCode1
Frame-wise Action Representations for Long Videos via Sequence Contrastive LearningCode1
Deep Self-Supervised Representation Learning for Free-Hand SketchCode1
DeiT III: Revenge of the ViTCode1
GAMC: An Unsupervised Method for Fake News Detection using Graph Autoencoder with MaskingCode1
Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth EstimationCode1
Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation OverlapCode1
What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable InsightsCode1
An Embarrassingly Simple Backdoor Attack on Self-supervised LearningCode1
Generalizing Event-Based Motion Deblurring in Real-World ScenariosCode1
Charting the Right Manifold: Manifold Mixup for Few-shot LearningCode1
Chasing Clouds: Differentiable Volumetric Rasterisation of Point Clouds as a Highly Efficient and Accurate Loss for Large-Scale Deformable 3D RegistrationCode1
ChemBERTa-2: Towards Chemical Foundation ModelsCode1
A self-supervised learning strategy for postoperative brain cavity segmentation simulating resectionsCode1
ConCL: Concept Contrastive Learning for Dense Prediction Pre-training in Pathology ImagesCode1
Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial RobustnessCode1
Show:102550
← PrevPage 14 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