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 2051–2100 of 5044 papers

TitleStatusHype
Adaptive Self-Supervised Learning Strategies for Dynamic On-Device LLM Personalization—0
PseudoNeg-MAE: Self-Supervised Point Cloud Learning using Conditional Pseudo-Negative Embeddings—0
Self-supervised Shape Completion via Involution and Implicit CorrespondencesCode0
Self-Supervised Representation Learning with Augmentations of Continuous Training Data Improves the Feel and Performance of Myoelectric Control—0
CA-MHFA: A Context-Aware Multi-Head Factorized Attentive Pooling for SSL-Based Speaker Verification—0
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
Simple Unsupervised Knowledge Distillation With Space Similarity—0
State space models, emergence, and ergodicity: How many parameters are needed for stable predictions?—0
Is Tokenization Needed for Masked Particle Modelling?—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
DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control—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
MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion—0
Frequency-Guided Masking for Enhanced Vision Self-Supervised LearningCode0
FGR-Net:Interpretable fundus imagegradeability classification based on deepreconstruction learning—0
Towards Automatic Assessment of Self-Supervised Speech Models using Rank—0
A Simple HMM with Self-Supervised Representations for Phone Segmentation—0
Self-supervised Learning for Acoustic Few-Shot Classification—0
On the Generalizability of Foundation Models for Crop Type MappingCode0
Interactive Masked Image Modeling for Multimodal Object Detection in Remote Sensing—0
Autoregressive Sequence Modeling for 3D Medical Image Representation—0
NEST-RQ: Next Token Prediction for Speech Self-Supervised Pre-Training—0
Exploring the Impact of Data Quantity on ASR in Extremely Low-resource Languages—0
Exploring SSL Discrete Tokens for Multilingual ASR—0
Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASRCode0
Exploiting Supervised Poison Vulnerability to Strengthen Self-Supervised DefenseCode0
Electrocardiogram Report Generation and Question Answering via Retrieval-Augmented Self-Supervised Modeling—0
Self-Supervised Learning of Iterative Solvers for Constrained Optimization—0
Digital Volumetric Biopsy Cores Improve Gleason Grading of Prostate Cancer Using Deep Learning—0
Virtual Node Generation for Node Classification in Sparsely-Labeled Graphs—0
What to align in multimodal contrastive learning?—0
Bridging Domain Gap of Point Cloud Representations via Self-Supervised Geometric Augmentation—0
Data Collection-free Masked Video Modeling—0
Cross-Modal Self-Supervised Learning with Effective Contrastive Units for LiDAR Point CloudsCode0
Hierarchical Multi-Label Classification with Missing Information for Benthic Habitat ImageryCode0
Label-free Monitoring of Self-Supervised Learning Progress—0
Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget—0
ECG Biometric Authentication Using Self-Supervised Learning for IoT Edge Sensors—0
GS-PT: Exploiting 3D Gaussian Splatting for Comprehensive Point Cloud Understanding via Self-supervised Learning—0
Audio-Guided Fusion Techniques for Multimodal Emotion Analysis—0
SS-BRPE: Self-Supervised Blind Room Parameter Estimation Using Attention MechanismsCode0
Explicit Mutual Information Maximization for Self-Supervised Learning—0
UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activity—0
An Analysis of Linear Complexity Attention Substitutes with BEST-RQ—0
PIETRA: Physics-Informed Evidential Learning for Traversing Out-of-Distribution Terrain—0
Show:102550
← PrevPage 42 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