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 1351–1400 of 5044 papers

TitleStatusHype
Self-Supervised Spatially Variant PSF Estimation for Aberration-Aware Depth-from-Defocus—0
Self-Supervised Learning with Generative Adversarial Networks for Electron Microscopy—0
Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder—0
VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image AnalysisCode3
Video as the New Language for Real-World Decision Making—0
LocalGCL: Local-aware Contrastive Learning for Graphs—0
SKILL: Similarity-aware Knowledge distILLation for Speech Self-Supervised Learning—0
Text-guided HuBERT: Self-Supervised Speech Pre-training via Generative Adversarial Networks—0
Overcoming Pitfalls in Graph Contrastive Learning Evaluation: Toward Comprehensive Benchmarks—0
Self-Retrieval: End-to-End Information Retrieval with One Large Language ModelCode1
Toward Fully Self-Supervised Multi-Pitch EstimationCode1
DeepSet SimCLR: Self-supervised deep sets for improved pathology representation learning—0
Semi-supervised Counting via Pixel-by-pixel Density Distribution ModellingCode0
The Common Stability Mechanism behind most Self-Supervised Learning ApproachesCode0
Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off—0
Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised LearningCode1
Overcoming Dimensional Collapse in Self-supervised Contrastive Learning for Medical Image SegmentationCode0
Self-supervised Visualisation of Medical Image DatasetsCode0
Zero-Shot Pediatric Tuberculosis Detection in Chest X-Rays using Self-Supervised Learning—0
A Simple Framework Uniting Visual In-context Learning with Masked Image Modeling to Improve Ultrasound SegmentationCode0
Multi-organ Self-supervised Contrastive Learning for Breast Lesion Segmentation—0
Contextual Molecule Representation Learning from Chemical Reaction KnowledgeCode0
The Effect of Batch Size on Contrastive Self-Supervised Speech Representation LearningCode1
User-LLM: Efficient LLM Contextualization with User Embeddings—0
UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed GraphsCode1
Unsupervised learning based object detection using Contrastive Learning—0
Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors—0
Analysis of Using Sigmoid Loss for Contrastive Learning—0
OccFlowNet: Towards Self-supervised Occupancy Estimation via Differentiable Rendering and Occupancy Flow—0
EMO-SUPERB: An In-depth Look at Speech Emotion RecognitionCode2
Solar Panel Segmentation :Self-Supervised Learning Solutions for Imperfect Datasets—0
SLADE: Detecting Dynamic Anomalies in Edge Streams without Labels via Self-Supervised LearningCode1
Thyroid ultrasound diagnosis improvement via multi-view self-supervised learning and two-stage pre-training—0
Probing Self-supervised Learning Models with Target Speech Extraction—0
Target Speech Extraction with Pre-trained Self-supervised Learning Models—0
"Understanding AI": Semantic Grounding in Large Language Models—0
Knowledge-guided EEG Representation Learning—0
Tracking Changing Probabilities via Dynamic LearnersCode0
Learning Low-Rank Feature for Thorax Disease Classification—0
Advancing Human Action Recognition with Foundation Models trained on Unlabeled Public Videos—0
Scalable Graph Self-Supervised Learning—0
WERank: Towards Rank Degradation Prevention for Self-Supervised Learning Using Weight Regularization—0
Affine transformation estimation improves visual self-supervised learning—0
GraSSRep: Graph-Based Self-Supervised Learning for Repeat Detection in Metagenomic AssemblyCode0
SimMLP: Training MLPs on Graphs without SupervisionCode1
Switch EMA: A Free Lunch for Better Flatness and SharpnessCode1
Learning How To Ask: Cycle-Consistency Refines Prompts in Multimodal Foundation Models—0
Mixtures of Experts Unlock Parameter Scaling for Deep RLCode0
Leveraging Self-Supervised Instance Contrastive Learning for Radar Object Detection—0
UGMAE: A Unified Framework for Graph Masked Autoencoders—0
Show:102550
← PrevPage 28 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