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 4001–4050 of 5044 papers

TitleStatusHype
Visible and infrared self-supervised fusion trained on a single example—0
Vision-Language Modeling with Regularized Spatial Transformer Networks for All Weather Crosswind Landing of Aircraft—0
Vision Learners Meet Web Image-Text Pairs—0
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision—0
Vision Transformers: State of the Art and Research Challenges—0
Visual Lexicon: Rich Image Features in Language Space—0
Visually Guided Self Supervised Learning of Speech Representations—0
Visual Representation Learning with Stochastic Frame Prediction—0
Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations—0
ViTAR: Vision Transformer with Any Resolution—0
ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer—0
VLMs-Guided Representation Distillation for Efficient Vision-Based Reinforcement Learning—0
VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment—0
VRMM: A Volumetric Relightable Morphable Head Model—0
Watching Too Much Television is Good: Self-Supervised Audio-Visual Representation Learning from Movies and TV Shows—0
Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASR—0
Wav2Vec-Aug: Improved self-supervised training with limited data—0
Wav2vec-C: A Self-supervised Model for Speech Representation Learning—0
Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition—0
Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation—0
WavFT: Acoustic model finetuning with labelled and unlabelled data—0
Weakly Augmented Variational Autoencoder in Time Series Anomaly Detection—0
Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows—0
Weakly Supervised Class-Agnostic Motion Prediction for Autonomous Driving—0
Weakly-Supervised Speech Pre-training: A Case Study on Target Speech Recognition—0
Weakly-Supervised Surgical Phase Recognition—0
WeakSTIL: Weak whole-slide image level stromal tumor infiltrating lymphocyte scores are all you need—0
Wearable Accelerometer Foundation Models for Health via Knowledge Distillation—0
Wearable-Based Real-time Freezing of Gait Detection in Parkinson's Disease Using Self-Supervised Learning—0
Wearable data from subjects playing Super Mario, sitting university exams, or performing physical exercise help detect acute mood episodes via self-supervised learning—0
WeedCLR: Weed Contrastive Learning through Visual Representations with Class-Optimized Loss in Long-Tailed Datasets—0
WeedNet: A Foundation Model-Based Global-to-Local AI Approach for Real-Time Weed Species Identification and Classification—0
Weighted Ensemble Self-Supervised Learning—0
WeLM: A Well-Read Pre-trained Language Model for Chinese—0
WERank: Towards Rank Degradation Prevention for Self-Supervised Learning Using Weight Regularization—0
What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model—0
What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis—0
What Do We Maximize in Self-Supervised Learning?—0
What I See Is What You See: Joint Attention Learning for First and Third Person Video Co-analysis—0
What shapes the loss landscape of self-supervised learning?—0
What to align in multimodal contrastive learning?—0
When are Foundation Models Effective? Understanding the Suitability for Pixel-Level Classification Using Multispectral Imagery—0
When Does Contrastive Visual Representation Learning Work?—0
When do neural networks learn world models?—0
Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?—0
Wild Visual Navigation: Fast Traversability Learning via Pre-Trained Models and Online Self-Supervision—0
With Great Backbones Comes Great Adversarial Transferability—0
XAI for Self-supervised Clustering of Wireless Spectrum Activity—0
XLA: A Robust Unsupervised Data Augmentation Framework for Cross-Lingual NLP—0
XLVIN: eXecuted Latent Value Iteration Nets—0
Show:102550
← PrevPage 81 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