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 3701–3750 of 5044 papers

TitleStatusHype
Cross-modal Manifold Cutmix for Self-supervised Video Representation Learning—0
Physics Driven Deep Retinex Fusion for Adaptive Infrared and Visible Image FusionCode1
A Tale of Color Variants: Representation and Self-Supervised Learning in Fashion E-Commerce—0
Augmentation-Free Self-Supervised Learning on GraphsCode1
Unsupervised Domain Generalization by Learning a Bridge Across DomainsCode1
3rd Place: A Global and Local Dual Retrieval Solution to Facebook AI Image Similarity ChallengeCode1
Ablation study of self-supervised learning for image classificationCode0
Self-supervised Graph Learning for Occasional Group Recommendation—0
A Multi-Strategy based Pre-Training Method for Cold-Start Recommendation—0
SSDL: Self-Supervised Dictionary Learning—0
Self-Supervised Material and Texture Representation Learning for Remote Sensing TasksCode1
Novel Class Discovery in Semantic SegmentationCode1
Probabilistic Contrastive Loss for Self-Supervised Learning—0
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic SegmentationCode1
A Fast Knowledge Distillation Framework for Visual RecognitionCode1
Contrastive Adaptive Propagation Graph Neural Networks for Efficient Graph LearningCode0
The Surprising Effectiveness of Representation Learning for Visual ImitationCode1
CLAWS: Contrastive Learning with hard Attention and Weak Supervision—0
GANORCON: Are Generative Models Useful for Few-shot Segmentation?—0
Object-Aware Cropping for Self-Supervised LearningCode1
PreViTS: Contrastive Pretraining with Video Tracking Supervision—0
Your head is there to move you around: Goal-driven models of the primate dorsal pathway—0
UniDoc: Unified Pretraining Framework for Document Understanding—0
TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive?Code1
Container: Context Aggregation NetworksCode1
D2C: Diffusion-Decoding Models for Few-Shot Conditional GenerationCode1
Disentangled Contrastive Learning on Graphs—0
Graph Adversarial Self-Supervised Learning—0
Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions—0
MISS: Multi-Interest Self-Supervised Learning Framework for Click-Through Rate Prediction—0
MC-SSL0.0: Towards Multi-Concept Self-Supervised Learning—0
FROB: Few-shot ROBust Model for Classification and Out-of-Distribution Detection—0
In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domains—0
Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup—0
Self-supervised Autoregressive Domain Adaptation for Time Series DataCode1
Overcoming the Domain Gap in Contrastive Learning of Neural Action Representations—0
Do Invariances in Deep Neural Networks Align with Human Perception?Code0
Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions—0
Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image AnalysisCode1
Similarity Contrastive Estimation for Self-Supervised Soft Contrastive LearningCode1
Simple Contrastive Representation Adversarial Learning for NLP Tasks—0
SLA^2P: Self-supervised Anomaly Detection with Adversarial PerturbationCode1
Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurementsCode1
Self-Distilled Self-Supervised Representation LearningCode0
UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation—0
PSSL: Self-supervised Learning for Personalized Search with Contrastive SamplingCode0
Efficient Anomaly Detection Using Self-Supervised Multi-Cue Tasks—0
ViCE: Improving Dense Representation Learning by Superpixelization and Contrasting Cluster AssignmentCode0
Distribution Estimation to Automate Transformation Policies for Self-Supervision—0
Domain-Agnostic Clustering with Self-Distillation—0
Show:102550
← PrevPage 75 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