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 451–500 of 5044 papers

TitleStatusHype
TAGA: Self-supervised Learning for Template-free Animatable Gaussian Articulated Model—0
Spectral Informed Mamba for Robust Point Cloud Processing—0
Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature SpaceCode0
AVF-MAE++: Scaling Affective Video Facial Masked Autoencoders via Efficient Audio-Visual Self-Supervised LearningCode1
Adapting Pre-trained 3D Models for Point Cloud Video Understanding via Cross-frame Spatio-temporal Perception—0
Self-Supervised Learning for Color Spike Camera ReconstructionCode0
BOE-ViT: Boosting Orientation Estimation with Equivariance in Self-Supervised 3D Subtomogram Alignment—0
Multi-modal Vision Pre-training for Medical Image Analysis—0
Invisible Backdoor Attack against Self-supervised LearningCode1
Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution—0
Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis—0
UCM-VeID V2: A Richer Dataset and A Pre-training Method for UAV Cross-Modality Vehicle Re-Identification—0
STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor ScenesCode3
Metadata-Enhanced Speech Emotion Recognition: Augmented Residual Integration and Co-Attention in Two-Stage Fine-Tuning—0
PyG-SSL: A Graph Self-Supervised Learning ToolkitCode1
NetFlowGen: Leveraging Generative Pre-training for Network Traffic Dynamics—0
EmoReg: Directional Latent Vector Modeling for Emotional Intensity Regularization in Diffusion-based Voice Conversion—0
Calibre: Towards Fair and Accurate Personalized Federated Learning with Self-Supervised LearningCode3
Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models—0
Causal Speech Enhancement with Predicting Semantics based on Quantized Self-supervised Learning Features—0
Improving Generalization for AI-Synthesized Voice DetectionCode1
Towards Better Spherical Sliced-Wasserstein Distance Learning with Data-Adaptive Discriminative Projection Direction—0
Evaluating Self-Supervised Learning in Medical Imaging: A Benchmark for Robustness, Generalizability, and Multi-Domain Impact—0
Automatic Self-supervised Learning for Social Recommendations—0
RaSeRec: Retrieval-Augmented Sequential RecommendationCode1
AV-DTEC: Self-Supervised Audio-Visual Fusion for Drone Trajectory Estimation and ClassificationCode0
Where Did Your Model Learn That? Label-free Influence for Self-supervised LearningCode0
An OpenMind for 3D medical vision self-supervised learningCode2
BloomCoreset: Fast Coreset Sampling using Bloom Filters for Fine-Grained Self-Supervised LearningCode0
Learning for Cross-Layer Resource Allocation in MEC-Aided Cell-Free Networks—0
EnhancePPG: Improving PPG-based Heart Rate Estimation with Self-Supervision and Augmentation—0
Self-supervised Spatial-Temporal Learner for Precipitation NowcastingCode0
LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot LearningCode0
Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information BottleneckCode1
Score-based Generative Diffusion Models for Social RecommendationsCode1
DiffSim: Taming Diffusion Models for Evaluating Visual SimilarityCode1
Efficient Self-Supervised Video Hashing with Selective State SpacesCode1
ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal Forecasting—0
Scaling 4D Representations—0
Zero-Shot Generalization for Blockage Localization in mmWave Communication—0
ECG-Byte: A Tokenizer for End-to-End Generative Electrocardiogram Language ModelingCode1
Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and ReasoningCode1
Future Research Avenues for Artificial Intelligence in Digital Gaming: An Exploratory Report—0
Enhancing Internet of Things Security throughSelf-Supervised Graph Neural Networks—0
PBVS 2024 Solution: Self-Supervised Learning and Sampling Strategies for SAR Classification in Extreme Long-Tail Distribution—0
Harnessing Event Sensory Data for Error Pattern Prediction in Vehicles: A Language Model ApproachCode0
Generalizable Representation Learning for fMRI-based Neurological Disorder IdentificationCode0
MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond—0
FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation LearningCode2
Advancing Comprehensive Aesthetic Insight with Multi-Scale Text-Guided Self-Supervised Learning—0
Show:102550
← PrevPage 10 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