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 1651–1700 of 5044 papers

TitleStatusHype
Contextual Molecule Representation Learning from Chemical Reaction KnowledgeCode0
Plasticity-Optimized Complementary Networks for Unsupervised Continual LearningCode0
PixMIM: Rethinking Pixel Reconstruction in Masked Image ModelingCode0
Compound Figure Separation of Biomedical Images: Mining Large Datasets for Self-supervised LearningCode0
Compound Figure Separation of Biomedical Images with Side LossCode0
PFML: Self-Supervised Learning of Time-Series Data Without Representation CollapseCode0
PEFT for Speech: Unveiling Optimal Placement, Merging Strategies, and Ensemble TechniquesCode0
Rethinking and Simplifying Bootstrapped Graph LatentsCode0
PECoP: Parameter Efficient Continual Pretraining for Action Quality AssessmentCode0
PatchRot: A Self-Supervised Technique for Training Vision TransformersCode0
Comparing Self-Supervised Learning Models Pre-Trained on Human Speech and Animal Vocalizations for Bioacoustics ProcessingCode0
Self-supervised Label Augmentation via Input TransformationsCode0
Overcoming Dimensional Collapse in Self-supervised Contrastive Learning for Medical Image SegmentationCode0
Companion Animal Disease Diagnostics based on Literal-aware Medical Knowledge Graph Representation LearningCode0
Rethinking Pre-Trained Feature Extractor Selection in Multiple Instance Learning for Whole Slide Image ClassificationCode0
Feature-Suppressed Contrast for Self-Supervised Food Pre-trainingCode0
Features Based Adaptive Augmentation for Graph Contrastive LearningCode0
Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature SpaceCode0
Optimizing the Noise in Self-Supervised Learning: from Importance Sampling to Noise-Contrastive EstimationCode0
PARTICLE: Part Discovery and Contrastive Learning for Fine-grained RecognitionCode0
Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud Semantic SegmentationCode0
Rethinking Temperature in Graph Contrastive LearningCode0
Self-Supervised Learning of Color ConstancyCode0
Revisiting Self-Supervised Visual Representation LearningCode0
Open-source framework for detecting bias and overfitting for large pathology imagesCode0
On the Stepwise Nature of Self-Supervised LearningCode0
On the Transferability of Visual Features in Generalized Zero-Shot LearningCode0
On the Role of Discrete Tokenization in Visual Representation LearningCode0
On the Generalizability of Foundation Models for Crop Type MappingCode0
On the Generalization and Causal Explanation in Self-Supervised LearningCode0
On the Importance of Embedding Norms in Self-Supervised LearningCode0
On the Difficulty of Defending Self-Supervised Learning against Model ExtractionCode0
On the Out-of-Distribution Generalization of Self-Supervised LearningCode0
Online Semi-Supervised Learning in Contextual Bandits with Episodic RewardCode0
Mitigating Urban-Rural Disparities in Contrastive Representation Learning with Satellite ImageryCode0
Clustering-Based Representation Learning through Output Translation and Its Application to Remote--Sensing ImagesCode0
Online Unsupervised Learning of Visual Representations and CategoriesCode0
Extracting speaker and emotion information from self-supervised speech models via channel-wise correlationsCode0
Collaborative Unsupervised Visual Representation Learning from Decentralized DataCode0
Object discovery and representation networksCode0
CGCL: Collaborative Graph Contrastive Learning without Handcrafted Graph Data AugmentationsCode0
OAMixer: Object-aware Mixing Layer for Vision TransformersCode0
Object-Oriented Dynamics Learning through Multi-Level AbstractionCode0
Operational Latent SpacesCode0
Non-Neighbors Also Matter to Kriging: A New Contrastive-Prototypical LearningCode0
Collaborative Auto-encoding for Blind Image Quality AssessmentCode0
Cold PAWS: Unsupervised class discovery and addressing the cold-start problem for semi-supervised learningCode0
NoisyActions2M: A Multimedia Dataset for Video Understanding from Noisy LabelsCode0
Noise-Robust Keyword Spotting through Self-supervised PretrainingCode0
Noisier2Inverse: Self-Supervised Learning for Image Reconstruction with Correlated NoiseCode0
Show:102550
← PrevPage 34 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