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 3501–3550 of 5044 papers

TitleStatusHype
Self-Supervised Video Representation Learning with Meta-Contrastive Network—0
Self-Supervised Video Transformers for Isolated Sign Language Recognition—0
Self-supervised Visual Attribute Learning for Fashion Compatibility—0
Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey—0
Self-supervised visual learning for analyzing firearms trafficking activities on the Web—0
Self-supervised visual learning in the low-data regime: a comparative evaluation—0
Self-supervised Visual-LiDAR Odometry with Flip Consistency—0
Self-Supervised Visual Representation Learning Using Lightweight Architectures—0
Self-Supervised Visual Representation Learning via Residual Momentum—0
Self-Supervised Visual Representation Learning on Food Images—0
Self-Supervised Visual Representations Learning by Contrastive Mask Prediction—0
Self-Supervised Wasserstein Pseudo-Labeling for Semi-Supervised Image Classification—0
Self-supervised Human Activity Recognition by Learning to Predict Cross-Dimensional Motion—0
Self-Supervision by Prediction for Object Discovery in Videos—0
Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology—0
Self-Supervision Enhanced Feature Selection with Correlated Gates—0
Self-Supervision for Tackling Unsupervised Anomaly Detection: Pitfalls and Opportunities—0
Self-supervision meets kernel graph neural models: From architecture to augmentations—0
Self-supervision of Feature Transformation for Further Improving Supervised Learning—0
Self-supervision through Random Segments with Autoregressive Coding (RandSAC)—0
Self-supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection—0
Self-trained Panoptic Segmentation—0
SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning—0
SelfVC: Voice Conversion With Iterative Refinement using Self Transformations—0
SelfVIO: Self-Supervised Deep Monocular Visual-Inertial Odometry and Depth Estimation—0
SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks—0
SELMA3D challenge: Self-supervised learning for 3D light-sheet microscopy image segmentation—0
SELM: Speech Enhancement Using Discrete Tokens and Language Models—0
Semantic Communications for Wireless Sensing: RIS-aided Encoding and Self-supervised Decoding—0
Semantic decoupled representation learning for remote sensing image change detection—0
Semantic-Enhanced Image Clustering—0
SemanticFlow: A Self-Supervised Framework for Joint Scene Flow Prediction and Instance Segmentation in Dynamic Environments—0
Semantic Graph Consistency: Going Beyond Patches for Regularizing Self-Supervised Vision Transformers—0
Semantic Image Segmentation: Two Decades of Research—0
Semantic Positive Pairs for Enhancing Visual Representation Learning of Instance Discrimination methods—0
Semantics-Consistent Feature Search for Self-Supervised Visual Representation Learning—0
Semi-Supervised and Self-Supervised Collaborative Learning for Prostate 3D MR Image Segmentation—0
Semi-supervised binary classification with latent distance learning—0
Semi-Supervised Contrastive Learning for Remote Sensing: Identifying Ancient Urbanization in the South Central Andes—0
Semi-supervised Contrastive Learning with Similarity Co-calibration—0
Self-Supervised Image Captioning with CLIP—0
Semi-supervised Learning via Conditional Rotation Angle Estimation—0
Meta-Embedding as Auxiliary Task Regularization—0
Semi-Supervised Relational Contrastive Learning—0
Sense and Learn: Self-Supervision for Omnipresent Sensors—0
SEPT: Towards Efficient Scene Representation Learning for Motion Prediction—0
Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry—0
Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series—0
SeRP: Self-Supervised Representation Learning Using Perturbed Point Clouds—0
ShapeEmbed: a self-supervised learning framework for 2D contour quantification—0
Show:102550
← PrevPage 71 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