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 4151–4200 of 5044 papers

TitleStatusHype
Self-Ensemling for 3D Point Cloud Domain Adaption—0
Contextualized Spatio-Temporal Contrastive Learning with Self-SupervisionCode0
Exploring Temporal Granularity in Self-Supervised Video Representation Learning—0
Constrained Mean Shift Using Distant Yet Related Neighbors for Representation LearningCode0
On visual self-supervision and its effect on model robustness—0
Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularization—0
Training Robust Zero-Shot Voice Conversion Models with Self-supervised Features—0
Cross-modal Manifold Cutmix for Self-supervised Video Representation Learning—0
Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning—0
A Tale of Color Variants: Representation and Self-Supervised Learning in Fashion E-Commerce—0
A Multi-Strategy based Pre-Training Method for Cold-Start Recommendation—0
Ablation study of self-supervised learning for image classificationCode0
Self-supervised Graph Learning for Occasional Group Recommendation—0
SSDL: Self-Supervised Dictionary Learning—0
Probabilistic Contrastive Loss for Self-Supervised Learning—0
Contrastive Adaptive Propagation Graph Neural Networks for Efficient Graph LearningCode0
CLAWS: Contrastive Learning with hard Attention and Weak Supervision—0
UniDoc: Unified Pretraining Framework for Document Understanding—0
PreViTS: Contrastive Pretraining with Video Tracking Supervision—0
GANORCON: Are Generative Models Useful for Few-shot Segmentation?—0
Your head is there to move you around: Goal-driven models of the primate dorsal pathway—0
Graph Adversarial Self-Supervised Learning—0
Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions—0
Disentangled Contrastive Learning on Graphs—0
Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup—0
MC-SSL0.0: Towards Multi-Concept Self-Supervised Learning—0
FROB: Few-shot ROBust Model for Classification and Out-of-Distribution Detection—0
MISS: Multi-Interest Self-Supervised Learning Framework for Click-Through Rate Prediction—0
In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domains—0
Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions—0
Do Invariances in Deep Neural Networks Align with Human Perception?Code0
Overcoming the Domain Gap in Contrastive Learning of Neural Action Representations—0
Simple Contrastive Representation Adversarial Learning for NLP Tasks—0
Self-Distilled Self-Supervised Representation LearningCode0
ViCE: Improving Dense Representation Learning by Superpixelization and Contrasting Cluster AssignmentCode0
Distribution Estimation to Automate Transformation Policies for Self-Supervision—0
Efficient Anomaly Detection Using Self-Supervised Multi-Cue Tasks—0
UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation—0
PSSL: Self-supervised Learning for Personalized Search with Contrastive SamplingCode0
Domain-Agnostic Clustering with Self-Distillation—0
Learning Generalized Visual Odometry Using Position-Aware Optical Flow and Geometric Bundle Adjustment—0
Broad Adversarial Training with Data Augmentation in the Output Space—0
Decentralized Unsupervised Learning of Visual Representations—0
HoughCL: Finding Better Positive Pairs in Dense Self-supervised Learning—0
Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming—0
Boosting Supervised Learning Performance with Co-training—0
SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities—0
Towards Fully Self-Supervised Learning of Knowledge from Unstructured Text—0
Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech RecognitionCode0
Leveraging Uni-Modal Self-Supervised Learning for Multimodal Audio-visual Speech Recognition—0
Show:102550
← PrevPage 84 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