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 3951–4000 of 5044 papers

TitleStatusHype
Generative or Contrastive? Phrase Reconstruction for Better Sentence Representation Learning—0
Infusing Linguistic Knowledge of SMILES into Chemical Language Models—0
Rumor Detection with Self-supervised Learning on Texts and Social Graph—0
Less than Few: Self-Shot Video Instance Segmentation—0
Knowledgeable Salient Span Mask for Enhancing Language Models as Knowledge Base—0
Imposing Consistency for Optical Flow Estimation—0
Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts—0
Augmentation-Free Graph Contrastive Learning with Performance Guarantee—0
SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition—0
TOV: The Original Vision Model for Optical Remote Sensing Image Understanding via Self-supervised Learning—0
Self-Supervised Video Representation Learning with Motion-Contrastive Perception—0
Representation Learning by Detecting Incorrect Location EmbeddingsCode0
Divergence-aware Federated Self-Supervised LearningCode0
CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data—0
Transformer-Based Self-Supervised Learning for Emotion Recognition—0
Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning—0
Frequency Selective Augmentation for Video Representation Learning—0
Self-supervised learning for robust voice cloning—0
DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scores—0
MAESTRO: Matched Speech Text Representations through Modality Matching—0
MTI-Net: A Multi-Target Speech Intelligibility Prediction Model—0
VNIbCReg: VICReg with Neighboring-Invariance and better-Covariance Evaluated on Non-stationary Seismic Signal Time SeriesCode0
LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similarity—0
Federated Self-supervised Speech Representations: Are We There Yet?—0
A Wav2vec2-Based Experimental Study on Self-Supervised Learning Methods to Improve Child Speech Recognition—0
Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency—0
Repeat after me: Self-supervised learning of acoustic-to-articulatory mapping by vocal imitation—0
Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation—0
A Comparison of Deep Learning MOS Predictors for Speech Synthesis Quality—0
Unsupervised Data Selection via Discrete Speech Representation for ASR—0
The Vicomtech Spoofing-Aware Biometric System for the SASV Challenge—0
Interpretable Saliency Maps And Self-Supervised Learning For Generalized Zero Shot Medical Image Classification—0
Exemplar Learning for Medical Image Segmentation—0
Distortion-Aware Self-Supervised 360° Depth Estimation from A Single Equirectangular Projection Image—0
Mix-up Self-Supervised Learning for Contrast-agnostic Applications—0
End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation—0
WavFT: Acoustic model finetuning with labelled and unlabelled data—0
On the Efficiency of Integrating Self-supervised Learning and Meta-learning for User-defined Few-shot Keyword Spotting—0
Selecting task with optimal transport self-supervised learning for few-shot classification—0
Self-distillation Augmented Masked Autoencoders for Histopathological Image Classification—0
Analyzing the factors affecting usefulness of Self-Supervised Pre-trained Representations for Speech Recognition—0
How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning—0
Self-Supervised Light Field Depth Estimation Using Epipolar Plane Images—0
Learning neural audio features without supervision—0
Investigating Active-learning-based Training Data Selection for Speech Spoofing Countermeasure—0
S2-Net: Self-supervision Guided Feature Representation Learning for Cross-Modality Images—0
Curriculum learning for self-supervised speaker verification—0
Learning Optical Flow, Depth, and Scene Flow without Real-World Labels—0
Self-supervised Semantic Segmentation Grounded in Visual Concepts—0
Semi-supervised machine learning model for analysis of nanowire morphologies from transmission electron microscopy imagesCode0
Show:102550
← PrevPage 80 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