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 3101–3150 of 5044 papers

TitleStatusHype
Structurally Different Neural Network Blocks for the Segmentation of Atrial and Aortic Perivascular Adipose Tissue in Multi-centre CT Angiography Scans—0
DenseDINO: Boosting Dense Self-Supervised Learning with Token-Based Point-Level Consistency—0
Subgraph Networks Based Contrastive Learning—0
Green Steganalyzer: A Green Learning Approach to Image Steganalysis—0
OTF: Optimal Transport based Fusion of Supervised and Self-Supervised Learning Models for Automatic Speech Recognition—0
Simultaneous or Sequential Training? How Speech Representations Cooperate in a Multi-Task Self-Supervised Learning System—0
Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Work—0
HomE: Homography-Equivariant Video Representation LearningCode0
Masked Autoencoder for Unsupervised Video Summarization—0
Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?Code0
On the Robustness of Arabic Speech Dialect Identification—0
Automatic Data Augmentation for Domain Adapted Fine-Tuning of Self-Supervised Speech Representations—0
A Novel Driver Distraction Behavior Detection Method Based on Self-supervised Learning with Masked Image ModelingCode0
Some voices are too common: Building fair speech recognition systems using the Common Voice dataset—0
Improved Cross-Lingual Transfer Learning For Automatic Speech Translation—0
Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression—0
Feature Learning in Image Hierarchies using Functional Maximal Correlation—0
Augmentation-aware Self-supervised Learning with Conditioned ProjectorCode0
There is more to graphs than meets the eye: Learning universal features with self-supervision—0
Spectal Harmonics: Bridging Spectral Embedding and Matrix Completion in Self-Supervised Learning—0
Additional Positive Enables Better Representation Learning for Medical Images—0
Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion—0
SSL-CPCD: Self-supervised learning with composite pretext-class discrimination for improved generalisability in endoscopic image analysis—0
Quantifying Representation Reliability in Self-Supervised Learning ModelsCode0
MiniSUPERB: Lightweight Benchmark for Self-supervised Speech ModelsCode0
Leveraging Semantic Information for Efficient Self-Supervised Emotion Recognition with Audio-Textual Distilled Models—0
Learning Off-Road Terrain Traversability with Self-Supervisions Only—0
MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) RepresentationsCode0
Self-Supervised Learning of Action Affordances as Interaction Modes—0
Unsupervised Embedding Quality Evaluation—0
Image as First-Order Norm+Linear Autoregression: Unveiling Mathematical Invariance—0
Weakly-Supervised Speech Pre-training: A Case Study on Target Speech Recognition—0
Generalizable Low-Resource Activity Recognition with Diverse and Discriminative Representation Learning—0
MPE4G: Multimodal Pretrained Encoder for Co-Speech Gesture Generation—0
Reverse Engineering Self-Supervised Learning—0
Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss—0
Delving Deeper into Data Scaling in Masked Image Modeling—0
Spoofing Attacker Also Benefits from Self-Supervised Pretrained Model—0
Collaborative Auto-encoding for Blind Image Quality AssessmentCode0
Difference-Masking: Choosing What to Mask in Continued PretrainingCode0
Masked Modeling Duo for Speech: Specializing General-Purpose Audio Representation to Speech using Denoising Distillation—0
TranUSR: Phoneme-to-word Transcoder Based Unified Speech Representation Learning for Cross-lingual Speech Recognition—0
An Autoencoder-based Snow Drought Index—0
Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers?Code0
Atomic and Subgraph-aware Bilateral Aggregation for Molecular Representation Learning—0
ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer—0
EnSiam: Self-Supervised Learning With Ensemble Representations—0
Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning—0
Self-supervised representations in speech-based depression detection—0
SurgMAE: Masked Autoencoders for Long Surgical Video Analysis—0
Show:102550
← PrevPage 63 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