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
CHAPTER: Exploiting Convolutional Neural Network Adapters for Self-supervised Speech Models—0
ViewNet: Unsupervised Viewpoint Estimation from Conditional Generation—0
CL4CTR: A Contrastive Learning Framework for CTR PredictionCode1
Model Extraction Attack against Self-supervised Speech Models—0
Survey on Self-Supervised Multimodal Representation Learning and Foundation Models—0
On the Power of Foundation Models—0
CLIP2GAN: Towards Bridging Text with the Latent Space of GANs—0
Learning Dense Object Descriptors from Multiple Views for Low-shot Category GeneralizationCode1
Semi-supervised binary classification with latent distance learning—0
Exploring the Coordination of Frequency and Attention in Masked Image ModelingCode1
A Theoretical Study of Inductive Biases in Contrastive Learning—0
Human-machine Interactive Tissue Prototype Learning for Label-efficient Histopathology Image SegmentationCode1
Link Prediction with Non-Contrastive LearningCode0
BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular RepresentationCode0
Wild-Time: A Benchmark of in-the-Wild Distribution Shift over TimeCode1
Ladder Siamese Network: a Method and Insights for Multi-level Self-Supervised Learning—0
WSSL: Weighted Self-supervised Learning Framework For Image-inpaintingCode0
Pose-disentangled Contrastive Learning for Self-supervised Facial RepresentationCode1
Multi-Task Learning of Object State Changes from Uncurated VideosCode1
Distilling Knowledge from Self-Supervised Teacher by Embedding Graph AlignmentCode1
Reason from Context with Self-supervised Learning—0
Semantic Communications for Wireless Sensing: RIS-aided Encoding and Self-supervised Decoding—0
ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event ClassificationCode1
Self-Supervised Learning based on Heat Equation—0
Nonlinear Equivariant Imaging: Learning Multi-Parametric Tissue Mapping without Ground Truth for Compressive Quantitative MRI—0
On the Transferability of Visual Features in Generalized Zero-Shot LearningCode0
From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning ParadigmCode0
CLAWSAT: Towards Both Robust and Accurate Code ModelsCode0
Deep Projective Rotation Estimation through Relative Supervision—0
ESTAS: Effective and Stable Trojan Attacks in Self-supervised Encoders with One Target Unlabelled Sample—0
Simultaneously Learning Robust Audio Embeddings and balanced Hash codes for Query-by-Example—0
Normalizing Flows for Human Pose Anomaly DetectionCode1
EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal TokensCode1
Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in DrawingsCode1
Local Contrastive Feature learning for Tabular Data—0
Statistically unbiased prediction enables accurate denoising of voltage imaging dataCode1
CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical FlowCode2
Exploring WavLM on Speech Enhancement—0
Weighted Ensemble Self-Supervised Learning—0
MelHuBERT: A simplified HuBERT on Mel spectrogramsCode1
Self-Supervised Visual Representation Learning via Residual Momentum—0
Balanced Deep CCA for Bird Vocalization Detection—0
Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech TransformersCode0
EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual BackbonesCode2
CPT-V: A Contrastive Approach to Post-Training Quantization of Vision Transformers—0
Semi-Supervised and Self-Supervised Collaborative Learning for Prostate 3D MR Image Segmentation—0
Mitigating Urban-Rural Disparities in Contrastive Representation Learning with Satellite ImageryCode0
SelfOdom: Self-supervised Egomotion and Depth Learning via Bi-directional Coarse-to-Fine Scale Recovery—0
Masked Reconstruction Contrastive Learning with Information Bottleneck Principle—0
Robust Alzheimer's Progression Modeling using Cross-Domain Self-Supervised Deep Learning—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