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 701750 of 5044 papers

TitleStatusHype
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive LearningCode1
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic SegmentationCode1
MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple TargetsCode1
Stain-invariant self supervised learning for histopathology image analysisCode1
Learning from partially labeled data for multi-organ and tumor segmentationCode1
3D-CSL: self-supervised 3D context similarity learning for Near-Duplicate Video RetrievalCode1
miCSE: Mutual Information Contrastive Learning for Low-shot Sentence EmbeddingsCode1
On Web-based Visual Corpus Construction for Visual Document UnderstandingCode1
data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setupCode1
SLICER: Learning universal audio representations using low-resource self-supervised pre-trainingCode1
MAST: Multiscale Audio Spectrogram TransformersCode1
Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech ProcessingCode1
Self-supervised Character-to-Character Distillation for Text RecognitionCode1
Rethinking Low-level Features for Interest Point Detection and DescriptionCode1
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentationCode1
A simple, efficient and scalable contrastive masked autoencoder for learning visual representationsCode1
Self-Supervised Learning with Multi-View Rendering for 3D Point Cloud AnalysisCode1
Open-vocabulary Semantic Segmentation with Frozen Vision-Language ModelsCode1
Facial Video-based Remote Physiological Measurement via Self-supervised LearningCode1
Multitask Detection of Speaker Changes, Overlapping Speech and Voice Activity Using wav2vec 2.0Code1
Broken Neural Scaling LawsCode1
MOFormer: Self-Supervised Transformer model for Metal-Organic Framework Property PredictionCode1
Contrastive Representation Learning for Gaze EstimationCode1
Self-supervised Sparse Representation for Video Anomaly DetectionCode1
Neural Eigenfunctions Are Structured Representation LearnersCode1
Evidence of Vocal Tract Articulation in Self-Supervised Learning of SpeechCode1
Towards Sustainable Self-supervised LearningCode1
SSiT: Saliency-guided Self-supervised Image Transformer for Diabetic Retinopathy GradingCode1
Self-Supervised Learning via Maximum Entropy CodingCode1
Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?Code1
Self-Supervised Learning with Masked Image Modeling for Teeth Numbering, Detection of Dental Restorations, and Instance Segmentation in Dental Panoramic RadiographsCode1
Anomaly Detection Requires Better RepresentationsCode1
Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive LearningCode1
Unifying Graph Contrastive Learning with Flexible Contextual ScopesCode1
Sentence Representation Learning with Generative Objective rather than Contrastive ObjectiveCode1
How Mask Matters: Towards Theoretical Understandings of Masked AutoencodersCode1
H2RBox: Horizontal Box Annotation is All You Need for Oriented Object DetectionCode1
Visual Reinforcement Learning with Self-Supervised 3D RepresentationsCode1
Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the WildCode1
An Embarrassingly Simple Backdoor Attack on Self-supervised LearningCode1
On the Utility of Self-supervised Models for Prosody-related TasksCode1
Masked Motion Encoding for Self-Supervised Video Representation LearningCode1
Task Compass: Scaling Multi-task Pre-training with Task PrefixCode1
OPERA: Omni-Supervised Representation Learning with Hierarchical SupervisionsCode1
APSNet: Attention Based Point Cloud SamplingCode1
Self-supervised Learning for Label-Efficient Sleep Stage Classification: A Comprehensive EvaluationCode1
Dual-distribution discrepancy with self-supervised refinement for anomaly detection in medical imagesCode1
Revisiting Self-Supervised Contrastive Learning for Facial Expression RecognitionCode1
Temporal Feature Alignment in Contrastive Self-Supervised Learning for Human Activity RecognitionCode1
An Investigation into Whitening Loss for Self-supervised LearningCode1
Show:102550
← PrevPage 15 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