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 3151–3200 of 5044 papers

TitleStatusHype
Locally Constrained Representations in Reinforcement Learning—0
Local Manifold Augmentation for Multiview Semantic Consistency—0
Local Policy Improvement for Recommender Systems—0
Local-to-Global Self-Supervised Representation Learning for Diabetic Retinopathy Grading—0
LOHA: Direct Graph Spectral Contrastive Learning Between Low-pass and High-pass Views—0
Longitudinal Self-supervised Learning Using Neural Ordinary Differential Equation—0
Longitudinal Self-Supervision for COVID-19 Pathology Quantification—0
LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration—0
Low-Data Classification of Historical Music Manuscripts: A Few-Shot Learning Approach—0
Low-rank Optimal Transport: Approximation, Statistics and Debiasing—0
Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning—0
Low-Resource Self-Supervised Learning with SSL-Enhanced TTS—0
Low-Trace Adaptation of Zero-shot Self-supervised Blind Image Denoising—0
LPaintB: Learning to Paint from Self-Supervision—0
LSM-2: Learning from Incomplete Wearable Sensor Data—0
Longitudinal Self-Supervised Learning—0
LSTM Self-Supervision for Detailed Behavior Analysis—0
LV-MAE: Learning Long Video Representations through Masked-Embedding Autoencoders—0
LW-FedSSL: Resource-efficient Layer-wise Federated Self-supervised Learning—0
M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP—0
M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation—0
M^33D: Learning 3D priors using Multi-Modal Masked Autoencoders for 2D image and video understanding—0
MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion—0
Machine Unlearning in Contrastive Learning—0
MAEEG: Masked Auto-encoder for EEG Representation Learning—0
MAESTRO: Matched Speech Text Representations through Modality Matching—0
Making Self-supervised Learning Robust to Spurious Correlation via Learning-speed Aware Sampling—0
Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models—0
MAPGN: MAsked Pointer-Generator Network for sequence-to-sequence pre-training—0
MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning—0
Masked Autoencoder for Unsupervised Video Summarization—0
Masked Generative Extractor for Synergistic Representation and 3D Generation of Point Clouds—0
Masked Image Modeling Advances 3D Medical Image Analysis—0
Masked LoGoNet: Fast and Accurate 3D Image Analysis for Medical Domain—0
Masked Modeling Duo for Speech: Specializing General-Purpose Audio Representation to Speech using Denoising Distillation—0
Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input—0
Masked Modeling Duo: Towards a Universal Audio Pre-training Framework—0
Masked Momentum Contrastive Learning for Zero-shot Semantic Understanding—0
Masked Multi-Step Multivariate Time Series Forecasting with Future Information—0
Masked prediction tasks: a parameter identifiability view—0
Masked Reconstruction Contrastive Learning with Information Bottleneck Principle—0
Masked Self-Supervised Pre-Training for Text Recognition Transformers on Large-Scale Datasets—0
Masked Self-Supervision for Remaining Useful Lifetime Prediction in Machine Tools—0
Masked Siamese ConvNets—0
Masked Spatial-Spectral Autoencoders Are Excellent Hyperspectral Defenders—0
Mask Hierarchical Features For Self-Supervised Learning—0
MaskMatch: Boosting Semi-Supervised Learning Through Mask Autoencoder-Driven Feature Learning—0
MaskMol: Knowledge-guided Molecular Image Pre-Training Framework for Activity Cliffs—0
MASR: Multi-label Aware Speech Representation—0
MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors—0
Show:102550
← PrevPage 64 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