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 701–750 of 5044 papers

TitleStatusHype
OCC-MLLM-Alpha:Empowering Multi-modal Large Language Model for the Understanding of Occluded Objects with Self-Supervised Test-Time Learning—0
Decorrelation-based Self-Supervised Visual Representation Learning for Writer Identification—0
AgriCLIP: Adapting CLIP for Agriculture and Livestock via Domain-Specialized Cross-Model AlignmentCode1
Meta-TTT: A Meta-learning Minimax Framework For Test-Time Training—0
Local-to-Global Self-Supervised Representation Learning for Diabetic Retinopathy Grading—0
Pre-training with Synthetic Patterns for Audio—0
Contrastive Abstraction for Reinforcement Learning—0
On the Generalization and Causal Explanation in Self-Supervised LearningCode0
Radio Foundation Models: Pre-training Transformers for 5G-based Indoor Localization—0
AfriHuBERT: A self-supervised speech representation model for African languagesCode0
Self-supervised Auxiliary Learning for Texture and Model-based Hybrid Robust and Fair Featuring in Face Analysis—0
Multi-modal Cross-domain Self-supervised Pre-training for fMRI and EEG Fusion—0
TTT4Rec: A Test-Time Training Approach for Rapid Adaption in Sequential RecommendationCode0
Localizing Memorization in SSL Vision Encoders—0
A3: Active Adversarial Alignment for Source-Free Domain AdaptationCode0
A Survey of Spatio-Temporal EEG data Analysis: from Models to ApplicationsCode2
Packet Inspection Transformer: A Self-Supervised Journey to Unseen Malware Detection with Few Samples—0
SOAR: Self-supervision Optimized UAV Action Recognition with Efficient Object-Aware Pretraining—0
Description-based Controllable Text-to-Speech with Cross-Lingual Voice Control—0
Self-Supervised Learning of Deviation in Latent Representation for Co-speech Gesture Video Generation—0
RmGPT: Rotating Machinery Generative Pretrained Model—0
Exploring Acoustic Similarity in Emotional Speech and Music via Self-Supervised Representations—0
Prototype based Masked Audio Model for Self-Supervised Learning of Sound Event DetectionCode2
Emotional Dimension Control in Language Model-Based Text-to-Speech: Spanning a Broad Spectrum of Human Emotions—0
Block Expanded DINORET: Adapting Natural Domain Foundation Models for Retinal Imaging Without Catastrophic Forgetting—0
Trading through Earnings Seasons using Self-Supervised Contrastive Representation Learning—0
EMIT- Event-Based Masked Auto Encoding for Irregular Time SeriesCode0
Cross-Lingual Speech Emotion Recognition: Humans vs. Self-Supervised ModelsCode0
Face Forgery Detection with Elaborate BackboneCode1
Adaptive Self-Supervised Learning Strategies for Dynamic On-Device LLM Personalization—0
Benchmarking Domain Generalization Algorithms in Computational PathologyCode0
Self-Supervised Representation Learning with Augmentations of Continuous Training Data Improves the Feel and Performance of Myoelectric Control—0
Self-supervised Shape Completion via Involution and Implicit CorrespondencesCode0
PseudoNeg-MAE: Self-Supervised Point Cloud Learning using Conditional Pseudo-Negative Embeddings—0
CA-MHFA: A Context-Aware Multi-Head Factorized Attentive Pooling for SSL-Based Speaker Verification—0
ControlEdit: A MultiModal Local Clothing Image Editing MethodCode1
Protein-Mamba: Biological Mamba Models for Protein Function Prediction—0
Training Large ASR Encoders with Differential Privacy—0
Context-Aware Predictive Coding: A Representation Learning Framework for WiFi SensingCode0
State space models, emergence, and ergodicity: How many parameters are needed for stable predictions?—0
Simple Unsupervised Knowledge Distillation With Space Similarity—0
Is Tokenization Needed for Masked Particle Modelling?—0
DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control—0
On Vision Transformers for Classification Tasks in Side-Scan Sonar Imagery—0
Self-Supervised Learning via VICReg Enables Training of EMG Pattern Recognition Using Continuous Data with Unclear Labels—0
M-BEST-RQ: A Multi-Channel Speech Foundation Model for Smart Glasses—0
Multi-OCT-SelfNet: Integrating Self-Supervised Learning with Multi-Source Data Fusion for Enhanced Multi-Class Retinal Disease Classification—0
Context-Aware Predictive Coding: A Representation Learning Framework for WiFi SensingCode0
Towards Automatic Assessment of Self-Supervised Speech Models using Rank—0
Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERTCode1
Show:102550
← PrevPage 15 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