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 651–700 of 5044 papers

TitleStatusHype
On Partial Prototype Collapse in the DINO Family of Self-Supervised Methods—0
Learning Graph Quantized TokenizersCode1
All models are wrong, some are useful: Model Selection with Limited LabelsCode0
Normalizing self-supervised learning for provably reliable Change Point Detection—0
SiamSeg: Self-Training with Contrastive Learning for Unsupervised Domain Adaptation Semantic Segmentation in Remote SensingCode1
EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation LearningCode1
PORTAL: Scalable Tabular Foundation Models via Content-Specific TokenizationCode1
Stabilize the Latent Space for Image Autoregressive Modeling: A Unified PerspectiveCode2
Fusion from Decomposition: A Self-Supervised Approach for Image Fusion and Beyond—0
Self-Supervised Learning of Disentangled Representations for Multivariate Time-Series—0
Enhancing Speech Emotion Recognition through Segmental Average Pooling of Self-Supervised Learning Features—0
MultiCamCows2024 -- A Multi-view Image Dataset for AI-driven Holstein-Friesian Cattle Re-Identification on a Working Farm—0
MAX: Masked Autoencoder for X-ray Fluorescence in Geological InvestigationCode0
CONSULT: Contrastive Self-Supervised Learning for Few-shot Tumor Detection—0
Reducing Source-Private Bias in Extreme Universal Domain Adaptation—0
Graph Masked Autoencoder for Spatio-Temporal Graph Learning—0
EchoApex: A General-Purpose Vision Foundation Model for Echocardiography—0
Revisiting and Benchmarking Graph Autoencoders: A Contrastive Learning PerspectiveCode0
LADMIM: Logical Anomaly Detection with Masked Image Modeling in Discrete Latent Space—0
Learning to Customize Text-to-Image Diffusion In Diverse Context—0
Block-to-Scene Pre-training for Point Cloud Hybrid-Domain Masked Autoencoders—0
Learning General Representation of 12-Lead Electrocardiogram with a Joint-Embedding Predictive ArchitectureCode1
SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion PredictionCode1
A foundation model for generalizable disease diagnosis in chest X-ray imagesCode1
Distributionally robust self-supervised learning for tabular dataCode0
Non-transferable Pruning—0
Robust infrared small target detection using self-supervised and a contrario paradigms—0
Self-Supervised Learning for Real-World Object Detection: a Survey—0
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You ThinkCode5
Structure-Centric Robust Monocular Depth Estimation via Knowledge Distillation—0
CSSL: Contrastive Self-Supervised Learning for Dependency Parsing on Relatively Free Word Ordered and Morphologically Rich Low Resource Languages—0
Sylber: Syllabic Embedding Representation of Speech from Raw AudioCode2
Wearable-Based Real-time Freezing of Gait Detection in Parkinson's Disease Using Self-Supervised Learning—0
Self-supervised inter-intra period-aware ECG representation learning for detecting atrial fibrillation—0
CUBE360: Learning Cubic Field Representation for Monocular 360 Depth Estimation for Virtual Reality—0
Diffusion Auto-regressive Transformer for Effective Self-supervised Time Series ForecastingCode1
Rethinking Weak-to-Strong Augmentation in Source-Free Domain Adaptive Object Detection—0
Failure-Proof Non-Contrastive Self-Supervised Learning—0
SkillMatch: Evaluating Self-supervised Learning of Skill Relatedness—0
T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data—0
Self-Supervised Anomaly Detection in the Wild: Favor Joint Embeddings Methods—0
Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View SynthesisCode0
Enhancing Graph Self-Supervised Learning with Graph Interplay—0
Improving Node Representation by Boosting Target-Aware Contrastive Loss—0
CUDLE: Learning Under Label Scarcity to Detect Cannabis Use in Uncontrolled Environments—0
Self-supervised Spatio-Temporal Graph Mask-Passing Attention Network for Perceptual Importance Prediction of Multi-point Tactility—0
DiffKillR: Killing and Recreating Diffeomorphisms for Cell Annotation in Dense Microscopy ImagesCode0
SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual RepresentationsCode0
BiSSL: Enhancing the Alignment Between Self-Supervised Pretraining and Downstream Fine-Tuning via Bilevel Optimization—0
SSL-NBV: A Self-Supervised-Learning-Based Next-Best-View algorithm for Efficient 3D Plant Reconstruction by a Robot—0
Show:102550
← PrevPage 14 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