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 4501–4550 of 5044 papers

TitleStatusHype
Preserving Node Distinctness in Graph Autoencoders via Similarity Distillation—0
Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning—0
Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model—0
Pre-Trained Models: Past, Present and Future—0
Pretraining Billion-scale Geospatial Foundational Models on Frontier—0
Pre-training Everywhere: Parameter-Efficient Fine-Tuning for Medical Image Analysis via Target Parameter Pre-training—0
Pre-training with Synthetic Patterns for Audio—0
PreViTS: Contrastive Pretraining with Video Tracking Supervision—0
Understanding and Improving Transfer Learning of Deep Models via Neural Collapse—0
Probabilistic Contrastive Loss for Self-Supervised Learning—0
Probabilistic Self-supervised Learning via Scoring Rules Minimization—0
Probing for Phonology in Self-Supervised Speech Representations: A Case Study on Accent Perception—0
Probing Self-supervised Learning Models with Target Speech Extraction—0
Probing Speaker-specific Features in Speaker Representations—0
Probing the Mid-level Vision Capabilities of Self-Supervised Learning—0
ProFeAT: Projected Feature Adversarial Training for Self-Supervised Learning of Robust Representations—0
Progressive Multi-Scale Self-Supervised Learning for Speech Recognition—0
Progressive Residual Extraction based Pre-training for Speech Representation Learning—0
CtxMIM: Context-Enhanced Masked Image Modeling for Remote Sensing Image Understanding—0
PromptMono: Cross Prompting Attention for Self-Supervised Monocular Depth Estimation in Challenging Environments—0
ProsAudit, a prosodic benchmark for self-supervised speech models—0
Prosodic Structure Beyond Lexical Content: A Study of Self-Supervised Learning—0
Prospective Role of Foundation Models in Advancing Autonomous Vehicles—0
Protein-ligand binding representation learning from fine-grained interactions—0
Protein-Mamba: Biological Mamba Models for Protein Function Prediction—0
Prototype Augmentation and Self-Supervision for Incremental Learning—0
Prototype-Guided Diffusion for Digital Pathology: Achieving Foundation Model Performance with Minimal Clinical Data—0
Prototypical Contrastive Predictive Coding—0
ProtoVAE: Prototypical Networks for Unsupervised Disentanglement—0
1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities—0
Proxyless Neural Architecture Adaptation for Supervised Learning and Self-Supervised Learning—0
Pruning All-Rounder: Rethinking and Improving Inference Efficiency for Large Vision Language Models—0
Pseudo-Data based Self-Supervised Federated Learning for Classification of Histopathological Images—0
Pseudo-label Refinement for Improving Self-Supervised Learning Systems—0
PseudoNeg-MAE: Self-Supervised Point Cloud Learning using Conditional Pseudo-Negative Embeddings—0
PSG-MAE: Robust Multitask Sleep Event Monitoring using Multichannel PSG Reconstruction and Inter-channel Contrastive Learning—0
PT-Tuning: Bridging the Gap between Time Series Masked Reconstruction and Forecasting via Prompt Token Tuning—0
Pushing the limits of self-supervised speaker verification using regularized distillation framework—0
QIRL: Boosting Visual Question Answering via Optimized Question-Image Relation Learning—0
QK Iteration: A Self-Supervised Representation Learning Algorithm for Image Similarity—0
Q-Match: Self-Supervised Learning by Matching Distributions Induced by a Queue—0
Quality-aware Pre-trained Models for Blind Image Quality Assessment—0
Radar Signal Recognition through Self-Supervised Learning and Domain Adaptation—0
Radio Foundation Models: Pre-training Transformers for 5G-based Indoor Localization—0
RADLER: Radar Object Detection Leveraging Semantic 3D City Models and Self-Supervised Radar-Image Learning—0
RAEncoder: A Label-Free Reversible Adversarial Examples Encoder for Dataset Intellectual Property Protection—0
RAMP: Retrieval-Augmented MOS Prediction via Confidence-based Dynamic Weighting—0
Random Walks in Self-supervised Learning for Triangular Meshes—0
RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank—0
3D Unsupervised Region-Aware Registration Transformer—0
Show:102550
← PrevPage 91 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