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 2101–2150 of 5044 papers

TitleStatusHype
Spatial-Temporal Graph Learning with Adversarial Contrastive AdaptationCode1
Graph Self-Supervised Learning for Endoscopic Image MatchingCode0
RedMotion: Motion Prediction via Redundancy ReductionCode1
Enhanced Masked Image Modeling for Analysis of Dental Panoramic RadiographsCode0
MTN: Forensic Analysis of MP4 Video Files Using Graph Neural NetworksCode0
HomoGCL: Rethinking Homophily in Graph Contrastive LearningCode1
Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and ProspectsCode2
UTOPIA: Unconstrained Tracking Objects without Preliminary Examination via Cross-Domain Adaptation—0
Label-noise-tolerant medical image classification via self-attention and self-supervised learning—0
Evaluation of Speech Representations for MOS predictionCode1
SSL4EO-L: Datasets and Foundation Models for Landsat ImageryCode4
MBrain: A Multi-channel Self-Supervised Learning Framework for Brain Signals—0
BrainNet: Epileptic Wave Detection from SEEG with Hierarchical Graph Diffusion Learning—0
Simplified Temporal Consistency Reinforcement LearningCode1
A Comparison of Self-Supervised Pretraining Approaches for Predicting Disease Risk from Chest Radiograph Images—0
Pushing the Limits of Unsupervised Unit Discovery for SSL Speech RepresentationCode1
Description-Enhanced Label Embedding Contrastive Learning for Text ClassificationCode0
Multi-Temporal Relationship Inference in Urban AreasCode0
TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series ForecastingCode2
SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?Code1
Self-supervised Learning and Graph Classification under Heterophily—0
Feature Normalization for Fine-tuning Self-Supervised Models in Speech Enhancement—0
MCR-Data2vec 2.0: Improving Self-supervised Speech Pre-training via Model-level Consistency Regularization—0
Malafide: a novel adversarial convolutive noise attack against deepfake and spoofing detection systemsCode0
GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition—0
Rethinking Polyp Segmentation from an Out-of-Distribution PerspectiveCode0
Semi-supervised learning made simple with self-supervised clusteringCode1
iSLAM: Imperative SLAMCode1
Is Anisotropy Inherent to Transformers?—0
CARL-G: Clustering-Accelerated Representation Learning on Graphs—0
Reducing Barriers to Self-Supervised Learning: HuBERT Pre-training with Academic Compute—0
Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient EncoderCode0
TS-MoCo: Time-Series Momentum Contrast for Self-Supervised Physiological Representation LearningCode1
What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model—0
Liquidity takers behavior representation through a contrastive learning approach—0
One-shot Learning for Channel Estimation in Massive MIMO Systems—0
Exploring Effective Mask Sampling Modeling for Neural Image Compression—0
DocAligner: Annotating Real-world Photographic Document Images by Simply Taking Pictures—0
A Large-Scale Analysis on Self-Supervised Video Representation Learning—0
CrossMoCo: Multi-modal Momentum Contrastive Learning for Point CloudCode0
Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio MaskingCode0
On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail LearningCode1
Regularizing with Pseudo-Negatives for Continual Self-Supervised LearningCode0
Understanding Masked Autoencoders via Hierarchical Latent Variable ModelsCode0
Contrastive Representation Disentanglement for Clustering—0
Context-Aware Self-Supervised Learning of Whole Slide Images—0
Migrate Demographic Group For Fair GNNs—0
Multimodal Learning Without Labeled Multimodal Data: Guarantees and ApplicationsCode1
A study on the impact of Self-Supervised Learning on automatic dysarthric speech assessment—0
Coarse Is Better? A New Pipeline Towards Self-Supervised Learning with Uncurated Images—0
Show:102550
← PrevPage 43 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