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 2701–2750 of 5044 papers

TitleStatusHype
Medical Vision Language Pretraining: A survey—0
Optimizing Likelihood-free Inference using Self-supervised Neural Symmetry EmbeddingsCode0
Jumpstarting Surgical Computer Vision—0
The Counterattack of CNNs in Self-Supervised Learning: Larger Kernel Size might be All You Need—0
Non-Cartesian Self-Supervised Physics-Driven Deep Learning Reconstruction for Highly-Accelerated Multi-Echo Spiral fMRI—0
Prospective Role of Foundation Models in Advancing Autonomous Vehicles—0
Large-scale Training of Foundation Models for Wearable Biosignals—0
A Review of Machine Learning Methods Applied to Video Analysis Systems—0
Cross-BERT for Point Cloud Pretraining—0
Data Scarcity in Recommendation Systems: A Survey—0
An Experimental Study: Assessing the Combined Framework of WavLM and BEST-RQ for Text-to-Speech Synthesis—0
VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment—0
Evaluating Self-supervised Speech Models on a Taiwanese Hokkien CorpusCode0
Bootstrap Your Own Variance—0
Rethinking and Simplifying Bootstrapped Graph LatentsCode0
A Generative Self-Supervised Framework using Functional Connectivity in fMRI Data—0
Class-Discriminative Attention Maps for Vision Transformers—0
T3D: Advancing 3D Medical Vision-Language Pre-training by Learning Multi-View Visual Consistency—0
Bigger is not Always Better: The Effect of Context Size on Speech Pre-TrainingCode0
Disentangling the Effects of Data Augmentation and Format Transform in Self-Supervised Learning of Image Representations—0
DDxT: Deep Generative Transformer Models for Differential DiagnosisCode0
Beyond Accuracy: Statistical Measures and Benchmark for Evaluation of Representation from Self-Supervised Learning—0
Local Masking Meets Progressive Freezing: Crafting Efficient Vision Transformers for Self-Supervised LearningCode0
SASSL: Enhancing Self-Supervised Learning via Neural Style Transfer—0
Spectral Temporal Contrastive Learning—0
Perceptual Group Tokenizer: Building Perception with Iterative Grouping—0
InfoFlowNet: A Multi-head Attention-based Self-supervised Learning Model with Surrogate Approach for Uncovering Brain Effective Connectivity—0
Multilevel Saliency-Guided Self-Supervised Learning for Image Anomaly Detection—0
Stochastic Vision Transformers with Wasserstein Distance-Aware Attention—0
Informal Safety Guarantees for Simulated Optimizers Through Extrapolation from Partial Simulations—0
Self-Supervised Learning for Large-Scale Preventive Security Constrained DC Optimal Power Flow—0
StyleCap: Automatic Speaking-Style Captioning from Speech Based on Speech and Language Self-supervised Learning Models—0
SubZero: Subspace Zero-Shot MRI ReconstructionCode0
MultiModal-Learning for Predicting Molecular Properties: A Framework Based on Image and Graph Structures—0
BIM: Block-Wise Self-Supervised Learning with Masked Image Modeling—0
Making Self-supervised Learning Robust to Spurious Correlation via Learning-speed Aware Sampling—0
A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature ExtractorsCode0
Active Foundational Models for Fault Diagnosis of Electrical Motors—0
A-JEPA: Joint-Embedding Predictive Architecture Can Listen—0
VILLS -- Video-Image Learning to Learn Semantics for Person Re-Identification—0
Joint Supervised and Self-supervised Learning for MRI Reconstruction—0
Self-supervised OCT Image Denoising with Slice-to-Slice Registration and ReconstructionCode0
Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding—0
One-bit Supervision for Image Classification: Problem, Solution, and Beyond—0
Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation—0
Revisiting Supervision for Continual Representation LearningCode0
Contrastive Left-Right Wearable Sensors (IMUs) Consistency Matching for HAR—0
Echocardiogram Foundation Model -- Application 1: Estimating Ejection Fraction—0
Event Camera Data Dense Pre-training—0
Teaching Robots to Build Simulations of Themselves—0
Show:102550
← PrevPage 55 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