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 4601–4650 of 5044 papers

TitleStatusHype
Environment Predictive Coding for Embodied Agents—0
General-Purpose Speech Representation Learning through a Self-Supervised Multi-Granularity Framework—0
On Scaling Contrastive Representations for Low-Resource Speech Recognition—0
Decoupling the Role of Data, Attention, and Losses in Multimodal TransformersCode0
SwingBot: Learning Physical Features from In-hand Tactile Exploration for Dynamic Swing-up Manipulation—0
Supervised Momentum Contrastive Learning for Few-Shot Classification—0
Unified Framework for Feature Extraction based on Contrastive Learning—0
JigsawGAN: Auxiliary Learning for Solving Jigsaw Puzzles with Generative Adversarial Networks—0
Cross-domain few-shot learning with unlabelled data—0
SelfMatch: Combining Contrastive Self-Supervision and Consistency for Semi-Supervised Learning—0
Self-Supervised Representation Learning from Flow Equivariance—0
Task-driven Self-supervised Bi-channel Networks for Diagnosis of Breast Cancers with Mammography—0
A Multi-Stage Attentive Transfer Learning Framework for Improving COVID-19 Diagnosis—0
Self-Supervised Learning for Segmentation—0
Explicit homography estimation improves contrastive self-supervised learning—0
Estimating Galactic Distances From Images Using Self-supervised Representation Learning—0
Self-supervised Visual-LiDAR Odometry with Flip Consistency—0
Exploring Geometry-Aware Contrast and Clustering Harmonization for Self-Supervised 3D Object Detection—0
A Theory of Self-Supervised Framework for Few-Shot Learning—0
Self-Supervised Learning of Compressed Video Representations—0
Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud Semantic SegmentationCode0
Neural spatio-temporal reasoning with object-centric self-supervised learning—0
Shape Self-Correction for Unsupervised Point Cloud Understanding—0
Shuffle to Learn: Self-supervised learning from permutations via differentiable ranking—0
Contrast and Order Representations for Video Self-Supervised Learning—0
Self-Supervised Continuous Control without Policy Gradient—0
Self-supervised Disentangled Representation Learning—0
Self-Supervised Domain Adaptation for Forgery Localization of JPEG Compressed Images—0
Self-supervised representation learning via adaptive hard-positive mining—0
Run Away From your Teacher: a New Self-Supervised Approach Solving the Puzzle of BYOL—0
Parallel Detection-and-Segmentation Learning for Weakly Supervised Instance Segmentation—0
Erasure for Advancing: Dynamic Self-Supervised Learning for Commonsense Reasoning—0
Self-supervised Temporal Learning—0
SeLFVi: Self-Supervised Light-Field Video Reconstruction From Stereo VideoCode0
Online Adversarial Purification based on Self-supervised Learning—0
A Machine Teaching Framework for Scalable Recognition—0
Contrastive Self-Supervised Learning of Global-Local Audio-Visual Representations—0
Uncertainty-Aware Pseudo Label Refinery for Domain Adaptive Semantic Segmentation—0
TravelNet: Self-Supervised Physically Plausible Hand Motion Learning From Monocular Color Images—0
IntraTomo: Self-Supervised Learning-Based Tomography via Sinogram Synthesis and PredictionCode0
Self-Supervised Image Prior Learning With GMM From a Single Noisy ImageCode0
Exploring Balanced Feature Spaces for Representation Learning—0
Self-Supervised 3D Skeleton Action Representation Learning With Motion Consistency and Continuity—0
Self-supervised Adversarial Robustness for the Low-label, High-data Regime—0
Empirical Studies on the Convergence of Feature Spaces in Deep Learning—0
SLIM: Self-Supervised LiDAR Scene Flow and Motion Segmentation—0
XLA: A Robust Unsupervised Data Augmentation Framework for Cross-Lingual NLP—0
Hybrid Interest Modeling for Long-tailed Users—0
From Handheld to Unconstrained Object Detection: a Weakly-supervised On-line Learning Approach—0
Self-Supervised Multimodal Domino: in Search of Biomarkers for Alzheimer's DiseaseCode0
Show:102550
← PrevPage 93 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