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 2851–2900 of 5044 papers

TitleStatusHype
Self-Supervised Learning via Maximum Entropy CodingCode1
Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?Code1
A survey on Self Supervised learning approaches for improving Multimodal representation learning—0
MixMask: Revisiting Masking Strategy for Siamese ConvNetsCode0
HAVANA: Hard negAtiVe sAmples aware self-supervised coNtrastive leArning for Airborne laser scanning point clouds semantic segmentation—0
Anomaly Detection Requires Better RepresentationsCode1
Learning Transferable Adversarial Robust Representations via Multi-view Consistency—0
Effective Targeted Attacks for Adversarial Self-Supervised Learning—0
Rethinking Prototypical Contrastive Learning through Alignment, Uniformity and Correlation—0
Automatic separation of laminar-turbulent flows on aircraft wings and stabilisers via adaptive attention butterfly networkCode0
Depth Contrast: Self-Supervised Pretraining on 3DPM Images for Mining Material ClassificationCode0
Towards Efficient and Effective Self-Supervised Learning of Visual RepresentationsCode0
Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive LearningCode1
Unifying Graph Contrastive Learning with Flexible Contextual ScopesCode1
Test-Time Training for Graph Neural Networks—0
MCP: Self-supervised Pre-training for Personalized Chatbots with Multi-level Contrastive Sampling—0
Self-Supervised Learning Through Efference CopiesCode0
Learning Self-Regularized Adversarial Views for Self-Supervised Vision TransformersCode0
SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning—0
Sentence Representation Learning with Generative Objective rather than Contrastive ObjectiveCode1
Extracting speaker and emotion information from self-supervised speech models via channel-wise correlationsCode0
How Mask Matters: Towards Theoretical Understandings of Masked AutoencodersCode1
Data-Limited Tissue Segmentation using Inpainting-Based Self-Supervised Learning—0
Unsupervised Dense Nuclei Detection and Segmentation with Prior Self-activation Map For Histology Images—0
An Embarrassingly Simple Backdoor Attack on Self-supervised LearningCode1
The Hidden Uniform Cluster Prior in Self-Supervised Learning—0
LEAVES: Learning Views for Time-Series Data in Contrastive Learning—0
Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the WildCode1
Visual Reinforcement Learning with Self-Supervised 3D RepresentationsCode1
H2RBox: Horizontal Box Annotation is All You Need for Oriented Object DetectionCode1
Evaluating the Label Efficiency of Contrastive Self-Supervised Learning for Multi-Resolution Satellite Imagery—0
On Compressing Sequences for Self-Supervised Speech Models—0
Self-Supervised Learning of Linear Precoders under Non-Linear PA Distortion for Energy-Efficient Massive MIMO Systems—0
On the Utility of Self-supervised Models for Prosody-related TasksCode1
Self-supervised video pretraining yields robust and more human-aligned visual representations—0
Masked Motion Encoding for Self-Supervised Video Representation LearningCode1
Task Compass: Scaling Multi-task Pre-training with Task PrefixCode1
CoRRECT: A Deep Unfolding Framework for Motion-Corrected Quantitative R2* Mapping—0
Deep Active Ensemble Sampling For Image Classification—0
CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Tracking—0
Self-supervised debiasing using low rank regularization—0
Deep Spectro-temporal Artifacts for Detecting Synthesized Speech—0
APSNet: Attention Based Point Cloud SamplingCode1
Self-supervised Model Based on Masked Autoencoders Advance CT Scans Classification—0
OPERA: Omni-Supervised Representation Learning with Hierarchical SupervisionsCode1
Self-supervised Learning for Label-Efficient Sleep Stage Classification: A Comprehensive EvaluationCode1
Exploring Efficient-tuning Methods in Self-supervised Speech Models—0
Label-free segmentation from cardiac ultrasound using self-supervised learning—0
Exploiting map information for self-supervised learning in motion forecasting—0
Unsupervised Domain Adaptive Fundus Image Segmentation with Few Labeled Source Data—0
Show:102550
← PrevPage 58 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