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 2351–2400 of 5044 papers

TitleStatusHype
Embodied Concept Learner: Self-supervised Learning of Concepts and Mapping through Instruction Following—0
Inductive biases in deep learning models for weather prediction—0
Self-Supervised Video Similarity LearningCode1
Localized Region Contrast for Enhancing Self-Supervised Learning in Medical Image Segmentation—0
Synthetic Hard Negative Samples for Contrastive Learning—0
Micron-BERT: BERT-based Facial Micro-Expression RecognitionCode1
Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT—0
Incorporating Unlabelled Data into Bayesian Neural Networks—0
VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionCode1
Multi-Level Contrastive Learning for Dense Prediction TaskCode0
Defending Against Patch-based Backdoor Attacks on Self-Supervised LearningCode1
Self-Supervised Learning-Based Source Separation for Meeting Data—0
Self-Supervised learning for Neural Architecture Search (NAS)—0
Multi-Modal Representation Learning with Text-Driven Soft Masks—0
Knowledge Accumulation in Continually Learned Representations and the Issue of Feature ForgettingCode0
HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of ActionsCode0
Mask Hierarchical Features For Self-Supervised Learning—0
INoD: Injected Noise Discriminator for Self-Supervised Representation Learning in Agricultural Fields—0
Automatic Detection of Out-of-body Frames in Surgical Videos for Privacy Protection Using Self-supervised Learning and Minimal Labels—0
Self-Supervised Multimodal Learning: A SurveyCode2
Contrastive-Signal-Dependent Plasticity: Self-Supervised Learning in Spiking Neural CircuitsCode1
ISSTAD: Incremental Self-Supervised Learning Based on Transformer for Anomaly Detection and LocalizationCode0
Kaizen: Practical Self-supervised Continual Learning with Continual Fine-tuningCode1
Dynamic Conceptional Contrastive Learning for Generalized Category DiscoveryCode1
Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning—0
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual TasksCode3
Transformer-based Self-supervised Multimodal Representation Learning for Wearable Emotion Recognition—0
De-coupling and De-positioning Dense Self-supervised LearningCode0
Point2Vec for Self-Supervised Representation Learning on Point CloudsCode1
Are Data-driven Explanations Robust against Out-of-distribution Data?Code0
Data Efficient Contrastive Learning in Histopathology using Active SamplingCode0
Spatiotemporal Self-supervised Learning for Point Clouds in the WildCode1
Large-scale pretraining on pathological images for fine-tuning of small pathological benchmarksCode0
On the Stepwise Nature of Self-Supervised LearningCode0
Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need—0
Contrastive Learning Is Spectral Clustering On Similarity GraphCode1
Spatially Adaptive Self-Supervised Learning for Real-World Image DenoisingCode1
Explainable Artificial Intelligence Architecture for Melanoma Diagnosis Using Indicator Localization and Self-Supervised Learning—0
Learning Rotation-Equivariant Features for Visual Correspondence—0
Deep Augmentation: Self-Supervised Learning with Transformations in Activation Space—0
Federated Learning without Full Labels: A Survey—0
Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail DataCode1
Detecting Backdoors in Pre-trained EncodersCode1
PointGame: Geometrically and Adaptively Masked Auto-Encoder on Point Clouds—0
A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action RecognitionCode1
Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete LabelsCode1
Self-supervised Learning with Speech Modulation Dropout—0
Multi-view Feature Extraction based on Triple Contrastive Heads—0
Frozen Language Model Helps ECG Zero-Shot Learning—0
MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillationCode0
Show:102550
← PrevPage 48 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