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 651–700 of 5044 papers

TitleStatusHype
Blockwise Self-Supervised Learning at ScaleCode1
HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised LearningCode1
Exploring Image Augmentations for Siamese Representation Learning with Chest X-RaysCode1
Mutual Wasserstein Discrepancy Minimization for Sequential RecommendationCode1
Cross-Architectural Positive Pairs improve the effectiveness of Self-Supervised LearningCode1
Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance AssessmentCode1
Lexi: Self-Supervised Learning of the UI LanguageCode1
Self-Supervised Learning for Data Scarcity in a Fatigue Damage Prognostic ProblemCode1
ViT-AE++: Improving Vision Transformer Autoencoder for Self-supervised Medical Image RepresentationsCode1
A Survey on Self-supervised Learning: Algorithms, Applications, and Future TrendsCode1
CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPCode1
Nearest Neighbor-Based Contrastive Learning for Hyperspectral and LiDAR Data ClassificationCode1
Learning the Relation between Similarity Loss and Clustering Loss in Self-Supervised LearningCode1
Learning by Sorting: Self-supervised Learning with Group Ordering ConstraintsCode1
Learning Goal-Conditioned Policies Offline with Self-Supervised Reward ShapingCode1
MoBYv2AL: Self-supervised Active Learning for Image ClassificationCode1
PCRLv2: A Unified Visual Information Preservation Framework for Self-supervised Pre-training in Medical Image AnalysisCode1
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
Change-Aware Sampling and Contrastive Learning for Satellite ImagesCode1
Protoype-based Dataset ComparisonCode1
Disjoint Masking with Joint Distillation for Efficient Masked Image ModelingCode1
Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised LearningCode1
Deep Unfolded Tensor Robust PCA with Self-supervised LearningCode1
Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised LearningCode1
BEATs: Audio Pre-Training with Acoustic TokenizersCode1
Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and LanguageCode1
BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving ScenariosCode1
Transductive Linear Probing: A Novel Framework for Few-Shot Node ClassificationCode1
Weakly Supervised Semantic Segmentation for Large-Scale Point CloudCode1
Benchmarking Self-Supervised Learning on Diverse Pathology DatasetsCode1
Self-Supervised PPG Representation Learning Shows High Inter-Subject VariabilityCode1
Giga-SSL: Self-Supervised Learning for Gigapixel ImagesCode1
Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural FieldsCode1
Exploring Stochastic Autoregressive Image Modeling for Visual RepresentationCode1
Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image SynthesisCode1
CL4CTR: A Contrastive Learning Framework for CTR PredictionCode1
Learning Dense Object Descriptors from Multiple Views for Low-shot Category GeneralizationCode1
Exploring the Coordination of Frequency and Attention in Masked Image ModelingCode1
Human-machine Interactive Tissue Prototype Learning for Label-efficient Histopathology Image SegmentationCode1
Wild-Time: A Benchmark of in-the-Wild Distribution Shift over TimeCode1
Pose-disentangled Contrastive Learning for Self-supervised Facial RepresentationCode1
Multi-Task Learning of Object State Changes from Uncurated VideosCode1
ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event ClassificationCode1
Distilling Knowledge from Self-Supervised Teacher by Embedding Graph AlignmentCode1
Normalizing Flows for Human Pose Anomaly DetectionCode1
EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal TokensCode1
Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in DrawingsCode1
Statistically unbiased prediction enables accurate denoising of voltage imaging dataCode1
MelHuBERT: A simplified HuBERT on Mel spectrogramsCode1
Show:102550
← PrevPage 14 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