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

Showing 551600 of 5044 papers

TitleStatusHype
Spatial-Temporal Graph Learning with Adversarial Contrastive AdaptationCode1
HomoGCL: Rethinking Homophily in Graph Contrastive LearningCode1
Evaluation of Speech Representations for MOS predictionCode1
Pushing the Limits of Unsupervised Unit Discovery for SSL Speech RepresentationCode1
Simplified Temporal Consistency Reinforcement LearningCode1
SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?Code1
iSLAM: Imperative SLAMCode1
Semi-supervised learning made simple with self-supervised clusteringCode1
TS-MoCo: Time-Series Momentum Contrast for Self-Supervised Physiological Representation LearningCode1
On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail LearningCode1
Multimodal Learning Without Labeled Multimodal Data: Guarantees and ApplicationsCode1
Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level TasksCode1
Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline DataCode1
Graph Transformer for RecommendationCode1
Deep learning powered real-time identification of insects using citizen science dataCode1
Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution ShiftsCode1
Pre-Training Auto-Generated Volumetric Shapes for 3D Medical Image SegmentationCode1
Self-supervised Learning to Bring Dual Reversed Rolling Shutter Images AliveCode1
A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural NetworksCode1
LowDINO -- A Low Parameter Self Supervised Learning ModelCode1
DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech ModelsCode1
Matrix Information Theory for Self-Supervised LearningCode1
One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker VerificationCode1
Modulate Your Spectrum in Self-Supervised LearningCode1
Intrinsic Self-Supervision for Data Quality AuditsCode1
Learning high-level visual representations from a child's perspective without strong inductive biasesCode1
Label-Efficient Learning in Agriculture: A Comprehensive ReviewCode1
Revisiting pre-trained remote sensing model benchmarks: resizing and normalization mattersCode1
Denoised Self-Augmented Learning for Social RecommendationCode1
Scaling Speech Technology to 1,000+ LanguagesCode1
Multi-behavior Self-supervised Learning for RecommendationCode1
Zero-Shot Text Classification via Self-Supervised TuningCode1
Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking DistillationCode1
Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature IndividualizationCode1
Adaptive Graph Contrastive Learning for RecommendationCode1
A benchmark for computational analysis of animal behavior, using animal-borne tagsCode1
DiffUTE: Universal Text Editing Diffusion ModelCode1
Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant ClusteringCode1
Rethinking Data Augmentation for Tabular Data in Deep LearningCode1
GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-TrainingCode1
XTab: Cross-table Pretraining for Tabular TransformersCode1
PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud VideosCode1
Masked Trajectory Models for Prediction, Representation, and ControlCode1
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual RepresentationsCode1
Learning to Predict Navigational Patterns from Partial ObservationsCode1
ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot LearningCode1
Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised LearningCode1
A vector quantized masked autoencoder for speech emotion recognitionCode1
DocMAE: Document Image Rectification via Self-supervised Representation LearningCode1
CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image UnderstandingCode1
Show:102550
← PrevPage 12 of 101Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Pretraining: NoneImages & Text57.5Unverified
2Pretraining: ShEDImages & Text54.3Unverified
3Pretraining: e-MixImages & Text48.9Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50Accuracy91.7Unverified
2ResNet18Accuracy91.02Unverified
3MV-MRAccuracy89.67Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy93.89Unverified
2ResNet18average top-1 classification accuracy92.58Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy72.51Unverified
2ResNet18average top-1 classification accuracy69.31Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet50)Top-1 Accuracy82.64Unverified
2CorInfomax (ResNet18)Top-1 Accuracy80.48Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy51.84Unverified
2ResNet18average top-1 classification accuracy51.67Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet18)Top-1 Accuracy93.18Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet18)Top-1 Accuracy71.61Unverified
#ModelMetricClaimedVerifiedStatus
1Hybrid BYOL-S/CvTAccuracy67.2Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet50)Top-1 Accuracy54.86Unverified