SOTAVerified

Unsupervised Pre-training

Pre-training a neural network using unsupervised (self-supervised) auxiliary tasks on unlabeled data.

Papers

Showing 51100 of 265 papers

TitleStatusHype
ConStyle v2: A Strong Prompter for All-in-One Image RestorationCode1
Unsupervised Pre-Training For Data-Efficient Text-to-Speech On Low Resource LanguagesCode1
METRA: Scalable Unsupervised RL with Metric-Aware AbstractionCode1
Bag of Tricks and A Strong baseline for Image Copy DetectionCode1
Behavior From the Void: Unsupervised Active Pre-TrainingCode1
D^2LV: A Data-Driven and Local-Verification Approach for Image Copy DetectionCode1
SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual RepresentationsCode1
Improving Transformer-based Speech Recognition Using Unsupervised Pre-trainingCode1
Exact solutions to the nonlinear dynamics of learning in deep linear neural networksCode1
Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing DataCode1
OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised LearningCode1
BMRetriever: Tuning Large Language Models as Better Biomedical Text RetrieversCode1
Leveraging Pre-trained Checkpoints for Sequence Generation TasksCode1
Korean-Specific Dataset for Table Question AnsweringCode1
HIQL: Offline Goal-Conditioned RL with Latent States as ActionsCode1
MAGNeto: An Efficient Deep Learning Method for the Extractive Tags Summarization ProblemCode1
DOBF: A Deobfuscation Pre-Training Objective for Programming LanguagesCode1
DocILE Benchmark for Document Information Localization and ExtractionCode1
Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful LearnerCode1
Multilingual Constituency Parsing with Self-Attention and Pre-TrainingCode1
Patient Contrastive Learning: a Performant, Expressive, and Practical Approach to ECG ModelingCode1
Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage RetrievalCode1
ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object DetectionCode1
PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-trainingCode1
Unsupervised Semantic Segmentation by Contrasting Object Mask ProposalsCode1
ELECTRIcity: An Efficient Transformer for Non-Intrusive Load MonitoringCode1
CATE: Computation-aware Neural Architecture Encoding with TransformersCode1
FreePoint: Unsupervised Point Cloud Instance SegmentationCode1
Deep Features for CBIR with Scarce Data using Hebbian Learning0
BID: Boundary-Interior Decoding for Unsupervised Temporal Action Localization Pre-Trainin0
Deep Discriminative Model for Video Classification0
Deep Belief Networks Based Feature Generation and Regression for Predicting Wind Power0
Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR0
An Investigation of Noise Robustness for Flow-Matching-Based Zero-Shot TTS0
4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding0
Incomplete Multi-View Multi-label Learning via Disentangled Representation and Label Semantic Embedding0
Improving On-Screen Sound Separation for Open-Domain Videos with Audio-Visual Self-Attention0
Incorporating Unlabelled Data into Bayesian Neural Networks0
CUPre: Cross-domain Unsupervised Pre-training for Few-Shot Cell Segmentation0
Cross-Domain Training for Goal-Oriented Conversational Agents0
Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning0
Automatic Sexism Detection with Multilingual Transformer Models0
A Brief Summary of Interactions Between Meta-Learning and Self-Supervised Learning0
Corruption Is Not All Bad: Incorporating Discourse Structure into Pre-training via Corruption for Essay Scoring0
Convergence of gradient based pre-training in Denoising autoencoders0
Automated clinical coding using off-the-shelf large language models0
Foundation Model for Wireless Technology Recognition Using IQ Timeseries0
On Architectures and Training for Raw Waveform Feature Extraction in ASR0
Faster learning of deep stacked autoencoders on multi-core systems using synchronized layer-wise pre-training0
Author2Vec: A Framework for Generating User Embedding0
Show:102550
← PrevPage 2 of 6Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
115RDLsAccuracy (%)95Unverified
29RDLsAccuracy (%)94Unverified
33 RMDLAccuracy (%)93Unverified
4CNNAccuracy (%)73Unverified
5RMDLAccuracy (%)0.1Unverified
#ModelMetricClaimedVerifiedStatus
1RMDL (30 RDLs)Sensitivity (VEB)90.69Unverified
2Sensitivity89.1Unverified
3RMDL 3 RDLsSensitivity0.87Unverified