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 3301–3350 of 5044 papers

TitleStatusHype
Orchestra: Unsupervised Federated Learning via Globally Consistent ClusteringCode1
Continual Barlow Twins: continual self-supervised learning for remote sensing semantic segmentation—0
Active Learning Through a Covering LensCode1
GraphMAE: Self-Supervised Masked Graph AutoencodersCode2
AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking KeypointsCode1
DEER: Descriptive Knowledge Graph for Explaining Entity RelationshipsCode1
Learning Dense Reward with Temporal Variant Self-Supervision—0
Self-supervised 3D anatomy segmentation using self-distilled masked image transformer (SMIT)Code1
Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity RecognitionCode1
What's Behind the Mask: Understanding Masked Graph Modeling for Graph AutoencodersCode6
A theoretical framework for self-supervised MR image reconstruction using sub-sampling via variable density Noisier2NoiseCode1
Voice Activity Projection: Self-supervised Learning of Turn-taking EventsCode1
Robust and Efficient Medical Imaging with Self-SupervisionCode3
Free Lunch for Surgical Video Understanding by Distilling Self-SupervisionsCode1
Global Contrast Masked Autoencoders Are Powerful Pathological Representation LearnersCode1
Deploying self-supervised learning in the wild for hybrid automatic speech recognition—0
Self-Supervised Learning of Multi-Object Keypoints for Robotic Manipulation—0
HelixADMET: a robust and endpoint extensible ADMET system incorporating self-supervised knowledge transfer—0
On the Difficulty of Defending Self-Supervised Learning against Model ExtractionCode0
Manifold Characteristics That Predict Downstream Task PerformanceCode0
Proxyless Neural Architecture Adaptation for Supervised Learning and Self-Supervised Learning—0
Learning Representations for New Sound Classes With Continual Self-Supervised LearningCode1
Self-supervised Assisted Active Learning for Skin Lesion SegmentationCode1
Toward a Geometrical Understanding of Self-supervised Contrastive Learning—0
Self-Supervised Masking for Unsupervised Anomaly Detection and Localization—0
Embodied-Symbolic Contrastive Graph Self-Supervised Learning for Molecular Graphs—0
Near out-of-distribution detection for low-resolution radar micro-Doppler signaturesCode1
Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers—0
Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations—0
The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning—0
Choice of training label matters: how to best use deep learning for quantitative MRI parameter estimationCode0
Scene Consistency Representation Learning for Video Scene SegmentationCode1
An Empirical Study Of Self-supervised Learning Approaches For Object Detection With TransformersCode0
Self-Supervised Anomaly Detection in Computer Vision and Beyond: A Survey and Outlook—0
Multiplexed Immunofluorescence Brain Image Analysis Using Self-Supervised Dual-Loss Adaptive Masked AutoencoderCode1
Reconstruction Enhanced Multi-View Contrastive Learning for Anomaly Detection on Attributed Networks—0
Domain Invariant Masked Autoencoders for Self-supervised Learning from Multi-domains—0
Transformer-based Cross-Modal Recipe Embeddings with Large Batch Training—0
Self-supervised regression learning using domain knowledge: Applications to improving self-supervised denoising in imaging—0
CoDo: Contrastive Learning with Downstream Background Invariance for Detection—0
Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning—0
Anatomy-aware Self-supervised Learning for Anomaly Detection in Chest RadiographsCode1
Multimodal Semi-Supervised Learning for Text RecognitionCode1
Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker Information—0
Decoupled-and-Coupled Networks: Self-Supervised Hyperspectral Image Super-Resolution with Subpixel FusionCode2
Self-supervised Deep Unrolled Reconstruction Using Regularization by Denoising—0
The NT-Xent loss upper bound—0
IMU Based Deep Stride Length Estimation With Self-Supervised Learning—0
Crystal Twins: Self-supervised Learning for Crystalline Material Property Prediction—0
Mapping the landscape of histomorphological cancer phenotypes using self-supervised learning on unlabeled, unannotated pathology slidesCode1
Show:102550
← PrevPage 67 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