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 2651–2700 of 5044 papers

TitleStatusHype
Balancing Continual Learning and Fine-tuning for Human Activity Recognition—0
PEFT for Speech: Unveiling Optimal Placement, Merging Strategies, and Ensemble TechniquesCode0
Evaluating Fairness in Self-supervised and Supervised Models for Sequential Data—0
GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised LearningCode0
Zero-shot Active Learning Using Self Supervised Learning—0
Multimodal self-supervised learning for lesion localization—0
Freeze the backbones: A Parameter-Efficient Contrastive Approach to Robust Medical Vision-Language Pre-training—0
A Novel Transformer-Based Self-Supervised Learning Method to Enhance Photoplethysmogram Signal Artifact Detection—0
Relating Events and Frames Based on Self-Supervised Learning and Uncorrelated Conditioning for Unsupervised Domain Adaptation—0
An Asymmetric Augmented Self-Supervised Learning Method for Unsupervised Fine-Grained Image Hashing—0
Fast Adaptation for Human Pose Estimation via Meta-Optimization—0
Circuit Design and Efficient Simulation of Quantum Inner Product and Empirical Studies of Its Effect on Near-Term Hybrid Quantum-Classic Machine LearningCode0
Self-supervised learning for skin cancer diagnosis with limited training dataCode0
Improving Graph Contrastive Learning via Adaptive Positive Sampling—0
ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations—0
Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton SequenceCode0
Morphing Tokens Draw Strong Masked Image ModelsCode0
SSL-OTA: Unveiling Backdoor Threats in Self-Supervised Learning for Object Detection—0
Unifying Self-Supervised Clustering and Energy-Based Models—0
3DTINC: Time-Equivariant Non-Contrastive Learning for Predicting Disease Progression from Longitudinal OCTs—0
A Self Supervised StyleGAN for Image Annotation and Classification with Extremely Limited Labels—0
BAL: Balancing Diversity and Novelty for Active LearningCode0
Uncertainty as a Predictor: Leveraging Self-Supervised Learning for Zero-Shot MOS Prediction—0
STRIDE: Single-video based Temporally Continuous Occlusion-Robust 3D Pose EstimationCode0
Understanding normalization in contrastive representation learning and out-of-distribution detectionCode0
TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation—0
Leveraging Visual Supervision for Array-based Active Speaker Detection and LocalizationCode0
Meta Transfer of Self-Supervised Knowledge: Foundation Model in Action for Post-Traumatic Epilepsy Prediction—0
Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data HeterogeneityCode0
FusDom: Combining In-Domain and Out-of-Domain Knowledge for Continuous Self-Supervised LearningCode0
Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation—0
DMT: Comprehensive Distillation with Multiple Self-supervised Teachers—0
Self-supervised Learning for Enhancing Geometrical Modeling in 3D-Aware Generative Adversarial Network—0
Collaborative Learning for Annotation-Efficient Volumetric MR Image Segmentation—0
Efficiency-oriented approaches for self-supervised speech representation learning—0
CEIR: Concept-based Explainable Image Representation Learning—0
CONCSS: Contrastive-based Context Comprehension for Dialogue-appropriate Prosody in Conversational Speech Synthesis—0
T-MAE: Temporal Masked Autoencoders for Point Cloud Representation LearningCode0
CNC-Net: Self-Supervised Learning for CNC Machining Operations—0
Test-Time Domain Adaptation by Learning Domain-Aware Batch NormalizationCode0
SELM: Speech Enhancement Using Discrete Tokens and Language Models—0
A novel dual-stream time-frequency contrastive pretext tasks framework for sleep stage classificationCode0
Audio-visual fine-tuning of audio-only ASR models—0
Guided Diffusion from Self-Supervised Diffusion Features—0
Deep Anomaly Detection in Text—0
FastInject: Injecting Unpaired Text Data into CTC-based ASR training—0
Erasing Self-Supervised Learning Backdoor by Cluster Activation MaskingCode0
Novel View Synthesis with View-Dependent Effects from a Single Image—0
Towards Model-Based Data Acquisition for Subjective Multi-Task NLP ProblemsCode0
NearbyPatchCL: Leveraging Nearby Patches for Self-Supervised Patch-Level Multi-Class Classification in Whole-Slide ImagesCode0
Show:102550
← PrevPage 54 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