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 4801–4850 of 5044 papers

TitleStatusHype
Learning from Scale-Invariant Examples for Domain Adaptation in Semantic SegmentationCode0
BSS-CFFMA: Cross-Domain Feature Fusion and Multi-Attention Speech Enhancement Network based on Self-Supervised EmbeddingCode0
Self-supervised Learning of Motion CaptureCode0
When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive LearningCode0
Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised LearningCode0
Deep Learning with Tabular Data: A Self-supervised ApproachCode0
Deep learning based domain adaptation for mitochondria segmentation on EM volumesCode0
Augmentation-aware Self-supervised Learning with Conditioned ProjectorCode0
Difference-Masking: Choosing What to Mask in Continued PretrainingCode0
Deep Clustering with Diffused Sampling and Hardness-aware Self-distillationCode0
Audio Barlow Twins: Self-Supervised Audio Representation LearningCode0
DECAR: Deep Clustering for learning general-purpose Audio RepresentationsCode0
Learning from Memory: Non-Parametric Memory Augmented Self-Supervised Learning of Visual FeaturesCode0
Self-supervised learning of object pose estimation using keypoint predictionCode0
Unsupervised Image Classification for Deep Representation LearningCode0
Self-Supervised Learning of Part Mobility from Point Cloud SequenceCode0
ViT-2SPN: Vision Transformer-based Dual-Stream Self-Supervised Pretraining Networks for Retinal OCT ClassificationCode0
LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot LearningCode0
Self-Supervised Learning of Physics-Guided Reconstruction Neural Networks without Fully-Sampled Reference DataCode0
LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption GenerationCode0
LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related TasksCode0
BRIDLE: Generalized Self-supervised Learning with QuantizationCode0
Large-scale pretraining on pathological images for fine-tuning of small pathological benchmarksCode0
Large-Scale Hyperspectral Image Clustering Using Contrastive LearningCode0
All models are wrong, some are useful: Model Selection with Limited LabelsCode0
Self-supervised Learning of Rotation-invariant 3D Point Set Features using Transformer and its Self-distillationCode0
Language-Aware Multilingual Machine Translation with Self-Supervised LearningCode0
Decoupling the Role of Data, Attention, and Losses in Multimodal TransformersCode0
LaFAM: Unsupervised Feature Attribution with Label-free Activation MapsCode0
Knowledge Accumulation in Continually Learned Representations and the Issue of Feature ForgettingCode0
AdaProj: Adaptively Scaled Angular Margin Subspace Projections for Anomalous Sound Detection with Auxiliary Classification TasksCode0
AdaCrossNet: Adaptive Dynamic Loss Weighting for Cross-Modal Contrastive Point Cloud LearningCode0
Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio RepresentationCode0
All4One: Symbiotic Neighbour Contrastive Learning via Self-Attention and Redundancy ReductionCode0
De-coupling and De-positioning Dense Self-supervised LearningCode0
Unsupervised Natural Language Inference via Decoupled Multimodal Contrastive LearningCode0
Kit-Net: Self-Supervised Learning to Kit Novel 3D Objects into Novel 3D CavitiesCode0
Self-Supervised Learning Through Efference CopiesCode0
KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement LearningCode0
KB-Plugin: A Plug-and-play Framework for Large Language Models to Induce Programs over Low-resourced Knowledge BasesCode0
Self-Supervised Learning to Guide Scientifically Relevant Categorization of Martian Terrain ImagesCode0
Self-Supervised Learning to Prove Equivalence Between Straight-Line Programs via Rewrite RulesCode0
JOSENet: A Joint Stream Embedding Network for Violence Detection in Surveillance VideosCode0
Self-supervised learning unveils change in urban housing from street-level imagesCode0
Joint-task Self-supervised Learning for Temporal CorrespondenceCode0
Attention-based Contrastive Learning for Winograd SchemasCode0
DDxT: Deep Generative Transformer Models for Differential DiagnosisCode0
Self-Supervised Learning via Conditional Motion PropagationCode0
Self-supervised learning via inter-modal reconstruction and feature projection networks for label-efficient 3D-to-2D segmentationCode0
3D Face Reconstruction from A Single Image Assisted by 2D Face Images in the WildCode0
Show:102550
← PrevPage 97 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