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 51–100 of 5044 papers

TitleStatusHype
IMPA-HGAE:Intra-Meta-Path Augmented Heterogeneous Graph Autoencoder—0
Graph Neural Networks in Modern AI-aided Drug Discovery—0
EV-LayerSegNet: Self-supervised Motion Segmentation using Event Cameras—0
When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive LearningCode0
TADA: Training-free Attribution and Out-of-Domain Detection of Audio DeepfakesCode0
Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning—0
Rethinking Contrastive Learning in Session-based RecommendationCode0
LSM-2: Learning from Incomplete Wearable Sensor Data—0
Tone recognition in low-resource languages of North-East India: peeling the layers of SSL-based speech models—0
Prosodic Structure Beyond Lexical Content: A Study of Self-Supervised Learning—0
HGOT: Self-supervised Heterogeneous Graph Neural Network with Optimal Transport—0
Synthetic Speech Source Tracing using Metric Learning—0
Sounding Like a Winner? Prosodic Differences in Post-Match Interviews—0
MoCA: Multi-modal Cross-masked Autoencoder for Digital Health Measurements—0
Self-Supervised-ISAR-Net Enables Fast Sparse ISAR Imaging—0
GigaAM: Efficient Self-Supervised Learner for Speech RecognitionCode4
HASRD: Hierarchical Acoustic and Semantic Representation Disentanglement—0
PARROT: Synergizing Mamba and Attention-based SSL Pre-Trained Models via Parallel Branch Hadamard Optimal Transport for Speech Emotion Recognition—0
Getting More from Less: Transfer Learning Improves Sleep Stage Decoding Accuracy in Peripheral Wearable Devices—0
Towards Unified Neural Decoding with Brain Functional Network Modeling—0
Fine-tune Before Structured Pruning: Towards Compact and Accurate Self-Supervised Models for Speaker Diarization—0
A Cross Branch Fusion-Based Contrastive Learning Framework for Point Cloud Self-supervised Learning—0
MSDA: Combining Pseudo-labeling and Self-Supervision for Unsupervised Domain Adaptation in ASR—0
MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded KnowledgeCode0
Sparsity-Driven Parallel Imaging Consistency for Improved Self-Supervised MRI Reconstruction—0
A Survey of Generative Categories and Techniques in Multimodal Large Language Models—0
VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation ModelsCode2
Graph Positional Autoencoders as Self-supervised Learners—0
Subgraph Gaussian Embedding Contrast for Self-Supervised Graph Representation LearningCode0
Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM—0
Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action RecognitionCode0
IMTS is Worth Time Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series PredictionCode1
ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding—0
Pretraining Language Models to Ponder in Continuous SpaceCode1
CellCLAT: Preserving Topology and Trimming Redundancy in Self-Supervised Cellular Contrastive LearningCode0
Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysis—0
Supervised and self-supervised land-cover segmentation & classification of the Biesbosch wetlands—0
Training Articulatory Inversion Models for Interspeaker Consistency—0
Task-Oriented Low-Label Semantic Communication With Self-Supervised Learning—0
Causality and "In-the-Wild" Video-Based Person Re-ID: A Survey—0
A Contrastive Learning Foundation Model Based on Perfectly Aligned Sample Pairs for Remote Sensing Images—0
A Regularization-Guided Equivariant Approach for Image RestorationCode1
Automated data curation for self-supervised learning in underwater acoustic analysis—0
Advancing Video Self-Supervised Learning via Image Foundation ModelsCode0
Domain and Task-Focused Example Selection for Data-Efficient Contrastive Medical Image SegmentationCode0
WeedNet: A Foundation Model-Based Global-to-Local AI Approach for Real-Time Weed Species Identification and Classification—0
Eta-WavLM: Efficient Speaker Identity Removal in Self-Supervised Speech Representations Using a Simple Linear Equation—0
Reward-Driven Interaction: Enhancing Proactive Dialogue Agents through User Satisfaction Prediction—0
VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining—0
Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain—0
Show:102550
← PrevPage 2 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