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 3201–3250 of 5044 papers

TitleStatusHype
Visualizing and Understanding Contrastive LearningCode0
LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language ModelsCode1
Boosting Cross-Domain Speech Recognition with Self-SupervisionCode0
Distribution Regularized Self-Supervised Learning for Domain Adaptation of Semantic Segmentation—0
Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy AutoencodersCode2
Self-Supervised Learning for Videos: A SurveyCode0
Bag of Image Patch Embedding Behind the Success of Self-Supervised Learning—0
How Robust is Unsupervised Representation Learning to Distribution Shift?—0
Evaluating Self-Supervised Learning for Molecular Graph EmbeddingsCode1
DRAFT: A Novel Framework to Reduce Domain Shifting in Self-supervised Learning and Its Application to Children's ASR—0
Acoustic Modeling for End-to-End Empathetic Dialogue Speech Synthesis Using Linguistic and Prosodic Contexts of Dialogue History—0
Adapting Self-Supervised Vision Transformers by Probing Attention-Conditioned Masking ConsistencyCode1
CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World DomainsCode1
iBoot: Image-bootstrapped Self-Supervised Video Representation Learning—0
Patch-level Representation Learning for Self-supervised Vision TransformersCode1
The ZevoMOS entry to VoiceMOS Challenge 2022—0
Masked Siamese ConvNets—0
Self-Supervised Implicit Attention: Guided Attention by The Model Itself—0
Self-Supervised Learning of Image Scale and OrientationCode1
EDITnet: A Lightweight Network for Unsupervised Domain Adaptation in Speaker Verification—0
A Simple Data Mixing Prior for Improving Self-Supervised LearningCode1
Test-Time Adaptation for Visual Document Understanding—0
Astock: A New Dataset and Automated Stock Trading based on Stock-specific News Analyzing ModelCode2
On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis—0
RoSGAS: Adaptive Social Bot Detection with Reinforced Self-Supervised GNN Architecture SearchCode1
AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data—0
Quantitative Imaging Principles Improves Medical Image LearningCode0
Invariant Structure Learning for Better Generalization and Causal Explainability—0
Learning Fashion Compatibility from In-the-wild Images—0
Learning Task-Independent Game State Representations from Unlabeled Images—0
Virtual embeddings and self-consistency for self-supervised learning—0
Transformer-based Self-Supervised Fish Segmentation in Underwater Videos—0
Investigation of Ensemble features of Self-Supervised Pretrained Models for Automatic Speech Recognition—0
Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?Code0
Federated Momentum Contrastive Clustering—0
Masked Autoencoders are Robust Data AugmentorsCode1
SERE: Exploring Feature Self-relation for Self-supervised TransformerCode1
Is Self-Supervised Learning More Robust Than Supervised Learning?—0
Joint Encoder-Decoder Self-Supervised Pre-training for ASR—0
On Data Scaling in Masked Image Modeling—0
CASS: Cross Architectural Self-Supervision for Medical Image AnalysisCode1
Extending Momentum Contrast with Cross Similarity Consistency Regularization—0
On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning—0
Self-Knowledge Distillation based Self-Supervised Learning for Covid-19 Detection from Chest X-Ray Images—0
TriBYOL: Triplet BYOL for Self-Supervised Representation Learning—0
Layered Depth Refinement with Mask Guidance—0
Decoupled Self-supervised Learning for Non-Homophilous Graphs—0
FedNST: Federated Noisy Student Training for Automatic Speech Recognition—0
Physics and semantic informed multi-sensor calibration via optimization theory and self-supervised learning—0
Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable DataCode1
Show:102550
← PrevPage 65 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