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 2601–2650 of 5044 papers

TitleStatusHype
Seamless Multimodal Biometrics for Continuous Personalised Wellbeing Monitoring—0
Learning the Relation between Similarity Loss and Clustering Loss in Self-Supervised LearningCode1
Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching—0
REaaS: Enabling Adversarially Robust Downstream Classifiers via Robust Encoder as a Service—0
Skip-Attention: Improving Vision Transformers by Paying Less Attention—0
MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology—0
Event Camera Data Pre-training—0
Learning Goal-Conditioned Policies Offline with Self-Supervised Reward ShapingCode1
Learning by Sorting: Self-supervised Learning with Group Ordering ConstraintsCode1
MoBYv2AL: Self-supervised Active Learning for Image ClassificationCode1
A New Perspective to Boost Vision Transformer for Medical Image Classification—0
STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural VideosCode0
Argoverse 2: Next Generation Datasets for Self-Driving Perception and ForecastingCode2
PCRLv2: A Unified Visual Information Preservation Framework for Self-supervised Pre-training in Medical Image AnalysisCode1
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked AutoencodersCode3
Cross-modal Scalable Hierarchical Clustering in Hyperbolic space—0
Instance and Category Supervision are Alternate Learners for Continual Learning—0
Self-supervised Pre-training for Mirror Detection—0
Building3D: A Urban-Scale Dataset and Benchmarks for Learning Roof Structures from Point Clouds—0
HiVLP: Hierarchical Interactive Video-Language Pre-Training—0
Homeomorphism Alignment for Unsupervised Domain AdaptationCode0
Contrastive Continuity on Augmentation Stability Rehearsal for Continual Self-Supervised Learning—0
Contactless Pulse Estimation Leveraging Pseudo Labels and Self-Supervision—0
Protoype-based Dataset ComparisonCode1
Towards Effective Instance Discrimination Contrastive Loss for Unsupervised Domain AdaptationCode0
Learning from Noisy Data for Semi-Supervised 3D Object DetectionCode1
Chasing Clouds: Differentiable Volumetric Rasterisation of Point Clouds as a Highly Efficient and Accurate Loss for Large-Scale Deformable 3D RegistrationCode1
ToThePoint: Efficient Contrastive Learning of 3D Point Clouds via RecyclingCode0
SelfME: Self-Supervised Motion Learning for Micro-Expression Recognition—0
Change-Aware Sampling and Contrastive Learning for Satellite ImagesCode1
Spatio-Focal Bidirectional Disparity Estimation From a Dual-Pixel Image—0
Local-Guided Global: Paired Similarity Representation for Visual Reinforcement Learning—0
Exploring the Effect of Primitives for Compositional Generalization in Vision-and-LanguageCode0
Weakly Supervised Class-Agnostic Motion Prediction for Autonomous Driving—0
Evolved Part Masking for Self-Supervised Learning—0
Ponder: Point Cloud Pre-training via Neural Rendering—0
Tracking Passengers and Baggage Items using Multiple Overhead Cameras at Security CheckpointsCode0
Disjoint Masking with Joint Distillation for Efficient Masked Image ModelingCode1
DGFont++: Robust Deformable Generative Networks for Unsupervised Font GenerationCode2
Deep Active Learning Using Barlow Twins—0
3D Masked Modelling Advances Lesion Classification in Axial T2w Prostate MRI—0
Curator: Creating Large-Scale Curated Labelled Datasets using Self-Supervised Learning—0
Exploring Efficiency of Vision Transformers for Self-Supervised Monocular Depth EstimationCode0
GEDI: GEnerative and DIscriminative Training for Self-Supervised Learning—0
S2S-WTV: Seismic Data Noise Attenuation Using Weighted Total Variation Regularized Self-Supervised Learning—0
Don't Be So Sure! Boosting ASR Decoding via Confidence Relaxation—0
A Novel Self-Supervised Learning-Based Anomaly Node Detection Method Based on an Autoencoder in Wireless Sensor NetworksCode0
Benchmark for Uncertainty & Robustness in Self-Supervised LearningCode0
Understanding and Improving Transfer Learning of Deep Models via Neural Collapse—0
Offline Clustering Approach to Self-supervised Learning for Class-imbalanced Image Data—0
Show:102550
← PrevPage 53 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