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 4651–4700 of 5044 papers

TitleStatusHype
Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motionCode2
Self-adapting confidence estimation for stereoCode1
Multi-Mask Self-Supervised Learning for Physics-Guided Neural Networks in Highly Accelerated MRI—0
Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer—0
Variance-reduced Language Pretraining via a Mask Proposal Network—0
SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized with Semantic Segmentation for Autonomous Driving—0
Self-Supervised Learning of Audio-Visual Objects from VideoCode1
Spatiotemporal Contrastive Video Representation LearningCode1
Functional Regularization for Representation Learning: A Unified Theoretical PerspectiveCode0
Exploring Relations in Untrimmed Videos for Self-Supervised Learning—0
Self-supervised learning using consistency regularization of spatio-temporal data augmentation for action recognitionCode1
MusiCoder: A Universal Music-Acoustic Encoder Based on Transformers—0
Memory-augmented Dense Predictive Coding for Video Representation LearningCode1
Predicting What You Already Know Helps: Provable Self-Supervised Learning—0
Self-supervised Object Tracking with Cycle-consistent Siamese NetworksCode1
Learning Video Representations by Transforming Time—0
Leveraging Acoustic Images for Effective Self-Supervised Audio Representation LearningCode0
Self-supervised Learning of Point Clouds via Orientation EstimationCode1
Self-supervised Visual Attribute Learning for Fashion Compatibility—0
Distilling Visual Priors from Self-Supervised LearningCode1
Self-supervised learning through the eyes of a childCode1
Uncovering the structure of clinical EEG signals with self-supervised learningCode1
Leverage Unlabeled Data for Abstractive Speech Summarization with Self-Supervised Learning and Back-Summarization—0
Unselfie: Translating Selfies to Neutral-pose Portraits in the Wild—0
Learning from Scale-Invariant Examples for Domain Adaptation in Semantic SegmentationCode0
Self-supervised Neural Audio-Visual Sound Source Localization via Probabilistic Spatial Modeling—0
Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases—0
KOVIS: Keypoint-based Visual Servoing with Zero-Shot Sim-to-Real Transfer for Robotics ManipulationCode1
3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised LearningCode1
Representation Learning with Video Deep InfoMax—0
Crowdsourced 3D Mapping: A Combined Multi-View Geometry and Self-Supervised Learning ApproachCode1
Self-supervised Learning for Large-scale Item Recommendations—0
Federated Self-Supervised Learning of Multi-Sensor Representations for Embedded Intelligence—0
Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry ConsistencyCode1
Self-Supervised Learning Across Domains—0
Weakly and Partially Supervised Learning Frameworks for Anomaly DetectionCode1
Reliable Label Bootstrapping for Semi-Supervised LearningCode1
Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous NetworksCode1
CrossTransformers: spatially-aware few-shot transferCode1
Instance-aware Self-supervised Learning for Nuclei Segmentation—0
Video Representation Learning by Recognizing Temporal Transformations—0
Feature-metric Loss for Self-supervised Learning of Depth and EgomotionCode1
Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling—0
CSLNSpeech: solving extended speech separation problem with the help of Chinese sign languageCode0
Learning High-Level Policies for Model Predictive ControlCode1
Hierarchical Contrastive Motion Learning for Video Action Recognition—0
An Open-World Simulated Environment for Developmental Robotics—0
Improving Object Detection with Selective Self-supervised Self-training—0
Cross-Identity Motion Transfer for Arbitrary Objects through Pose-Attentive Video Reassembling—0
Self-Supervised Learning of Context-Aware Pitch Prosody Representations—0
Show:102550
← PrevPage 94 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