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 1051–1100 of 5044 papers

TitleStatusHype
Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders—0
Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and BeyondCode0
GraphAlign: Pretraining One Graph Neural Network on Multiple Graphs via Feature AlignmentCode1
SelfReDepth: Self-Supervised Real-Time Depth Restoration for Consumer-Grade SensorsCode0
Operational Latent SpacesCode0
M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation—0
Strengthening Network Intrusion Detection in IoT Environments with Self-Supervised Learning and Few Shot Learning—0
Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR ModelsCode0
Using Self-supervised Learning Can Improve Model FairnessCode1
Enhancing 2D Representation Learning with a 3D Prior—0
Learning to Edit Visual Programs with Self-SupervisionCode0
XRec: Large Language Models for Explainable RecommendationCode2
DDA: Dimensionality Driven Augmentation Search for Contrastive Learning in Laparoscopic SurgeryCode0
Cross-Dimensional Medical Self-Supervised Representation Learning Based on a Pseudo-3D Transformation—0
YODAS: Youtube-Oriented Dataset for Audio and Speech—0
An Unsupervised Approach for Periodic Source Detection in Time SeriesCode1
Whole Heart 3D+T Representation Learning Through Sparse 2D Cardiac MR ImagesCode1
Detecting Side Effects of Adverse Drug Reactions Through Drug-Drug Interactions Using Graph Neural Networks and Self-Supervised LearningCode0
Towards a General Recipe for Combinatorial Optimization with Multi-Filter GNNsCode0
MASA: Motion-aware Masked Autoencoder with Semantic Alignment for Sign Language RecognitionCode1
Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation LearningCode0
What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable InsightsCode1
SelfGNN: Self-Supervised Graph Neural Networks for Sequential RecommendationCode2
Fill in the Gap! Combining Self-supervised Representation Learning with Neural Audio Synthesis for Speech Inpainting—0
Rapid Wildfire Hotspot Detection Using Self-Supervised Learning on Temporal Remote Sensing DataCode0
Relation Modeling and Distillation for Learning with Noisy Labels—0
Rethinking Spectral Augmentation for Contrast-based Graph Self-Supervised Learning—0
MindSemantix: Deciphering Brain Visual Experiences with a Brain-Language Model—0
Enhancing Vision-Language Model with Unmasked Token AlignmentCode1
Anomaly Detection by Context Contrasting—0
Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation—0
Self-Supervised Learning Based Handwriting VerificationCode0
SCE-MAE: Selective Correspondence Enhancement with Masked Autoencoder for Self-Supervised Landmark Estimation—0
In-Context Symmetries: Self-Supervised Learning through Contextual World Models—0
Learning Shared RGB-D Fields: Unified Self-supervised Pre-training for Label-efficient LiDAR-Camera 3D PerceptionCode1
Spectral regularization for adversarially-robust representation learningCode0
TAGA: Text-Attributed Graph Self-Supervised Learning by Synergizing Graph and Text Mutual Transformations—0
ECG Semantic Integrator (ESI): A Foundation ECG Model Pretrained with LLM-Enhanced Cardiological TextCode1
Transformer Meets Gated Residual Networks To Enhance Photoplethysmogram Artifact Detection Informed by Mutual Information Neural Estimation—0
Retro: Reusing teacher projection head for efficient embedding distillation on Lightweight Models via Self-supervised Learning—0
Benchmarking Hierarchical Image Pyramid Transformer for the classification of colon biopsies and polyps in histopathology images—0
Automatic Data Curation for Self-Supervised Learning: A Clustering-Based ApproachCode3
Efficiently Training Deep-Learning Parametric Policies using Lagrangian Duality—0
Harmony: A Joint Self-Supervised and Weakly-Supervised Framework for Learning General Purpose Visual RepresentationsCode0
Awesome Multi-modal Object TrackingCode5
Efficiency for Free: Ideal Data Are Transportable RepresentationsCode1
Towards Imperceptible Backdoor Attack in Self-supervised LearningCode1
Masked Image Modelling for retinal OCT understandingCode0
PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis—0
Capsule Network Projectors are Equivariant and Invariant LearnersCode0
Show:102550
← PrevPage 22 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