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 3351–3400 of 5044 papers

TitleStatusHype
Random Teachers are Good TeachersCode0
Saliency Guided Contrastive Learning on Scene Images—0
Novel Class Discovery: an Introduction and Key ConceptsCode0
Self-supervised network distillation: an effective approach to exploration in sparse reward environmentsCode0
DrasCLR: A Self-supervised Framework of Learning Disease-related and Anatomy-specific Representation for 3D Medical Images—0
A Visual Representation-guided Framework with Global Affinity for Weakly Supervised Salient Object Detection—0
Normative framework for deriving neural networks with multi-compartmental neurons and non-Hebbian plasticity—0
An ASR-free Fluency Scoring Approach with Self-Supervised Learning—0
Unsupervised Learning on a DIET: Datum IndEx as Target Free of Self-Supervision, Reconstruction, Projector Head—0
A Novel Collaborative Self-Supervised Learning Method for Radiomic DataCode0
Self-supervised Cloth Reconstruction via Action-conditioned Cloth Tracking—0
Dual-Domain Self-Supervised Learning for Accelerated Non-Cartesian MRI Reconstruction—0
Front-End Adapter: Adapting Front-End Input of Speech based Self-Supervised Learning for Speech Recognition—0
Self-Supervised Representation Learning from Temporal Ordering of Automated Driving Sequences—0
ACE-VC: Adaptive and Controllable Voice Conversion using Explicitly Disentangled Self-supervised Speech Representations—0
Self-Supervised Learning for Modeling Gamma-ray Variability in Blazars—0
Audio-Visual Contrastive Learning with Temporal Self-Supervision—0
Text-Guided Scene Sketch-to-Photo Synthesis—0
Self-supervised learning of object pose estimation using keypoint predictionCode0
Semantic Image Segmentation: Two Decades of Research—0
Multidimensional Particle Filter for Long-Term Visual Teach and Repeat in Changing EnvironmentsCode0
Label-efficient Time Series Representation Learning: A Review—0
Transformer models: an introduction and catalog—0
ASR Bundestag: A Large-Scale political debate dataset in German—0
Self-supervised pseudo-colorizing of masked cellsCode0
Multispectral Contrastive Learning with Viewmaker NetworksCode0
ConMAE: Contour Guided MAE for Unsupervised Vehicle Re-IdentificationCode0
Self-supervised learning-based cervical cytology for the triage of HPV-positive women in resource-limited settings and low-data regime—0
Language-Aware Multilingual Machine Translation with Self-Supervised LearningCode0
Q-Match: Self-Supervised Learning by Matching Distributions Induced by a Queue—0
A Review of Predictive and Contrastive Self-supervised Learning for Medical Images—0
AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations—0
Multi-view Feature Extraction based on Dual Contrastive Head—0
Delving Deep into Simplicity Bias for Long-Tailed Image Recognition—0
The SSL Interplay: Augmentations, Inductive Bias, and Generalization—0
Multi-Task Self-Supervised Learning for Image Segmentation Task—0
Self-supervised Geometric Features Discovery via Interpretable Attentio for Vehicle Re-Identification and Beyond (Complete Version)Code0
Self-supervised Multi-view Disentanglement for Expansion of Visual Collections—0
Implicit Geometry and Interaction Embeddings Improve Few-Shot Molecular Property PredictionCode0
MOMA:Distill from Self-Supervised Teachers—0
Self-Supervised In-Domain Representation Learning for Remote Sensing Image Scene Classification—0
Self-Supervised Transformer Architecture for Change Detection in Radio Access Networks—0
Hyperbolic Contrastive Learning—0
Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial DefenseCode0
The unreasonable effectiveness of few-shot learning for machine translation—0
A Survey of Deep Learning: From Activations to Transformers—0
Distributed Traffic Synthesis and Classification in Edge Networks: A Federated Self-supervised Learning Approach—0
Towards Label-Efficient Incremental Learning: A SurveyCode0
Image-Based Vehicle Classification by Synergizing Features from Supervised and Self-Supervised Learning Paradigms—0
PointSmile: Point Self-supervised Learning via Curriculum Mutual Information—0
Show:102550
← PrevPage 68 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