SOTAVerified

Transfer Learning

Transfer Learning is a machine learning technique where a model trained on one task is re-purposed and fine-tuned for a related, but different task. The idea behind transfer learning is to leverage the knowledge learned from a pre-trained model to solve a new, but related problem. This can be useful in situations where there is limited data available to train a new model from scratch, or when the new task is similar enough to the original task that the pre-trained model can be adapted to the new problem with only minor modifications.

( Image credit: Subodh Malgonde )

Papers

Showing 151175 of 10307 papers

TitleStatusHype
TorchGeo: Deep Learning With Geospatial DataCode2
Deep Neural Networks to Detect Weeds from Crops in Agricultural Environments in Real-Time: A ReviewCode2
Learning Dense Representations of Phrases at ScaleCode2
Feature Learning in Infinite-Width Neural NetworksCode2
Deep learning for time series classificationCode2
Abstractive Summarization of Spoken andWritten Instructions with BERTCode2
Few-shot Knowledge Transfer for Fine-grained Cartoon Face GenerationCode2
TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device LearningCode2
Simplifying Paragraph-level Question Generation via Transformer Language ModelsCode2
AdapterFusion: Non-Destructive Task Composition for Transfer LearningCode2
CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documentsCode2
Cross-lingual Contextualized Topic Models with Zero-shot LearningCode2
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New OutlooksCode2
Unveiling COVID-19 from Chest X-ray with deep learning: a hurdles race with small dataCode2
jiant: A Software Toolkit for Research on General-Purpose Text Understanding ModelsCode2
Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerCode2
PubLayNet: largest dataset ever for document layout analysisCode2
TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational AgentsCode2
Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation LearningCode2
Pose-Normalized Image Generation for Person Re-identificationCode2
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature AlignmentCode1
Flowing Datasets with Wasserstein over Wasserstein Gradient FlowsCode1
TokAlign: Efficient Vocabulary Adaptation via Token AlignmentCode1
EfficientFER: EfficientNetv2 Based Deep Learning Approach for Facial Expression RecognitionCode1
Neuro2Semantic: A Transfer Learning Framework for Semantic Reconstruction of Continuous Language from Human Intracranial EEGCode1
Show:102550
← PrevPage 7 of 413Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1APCLIPAccuracy84.2Unverified
2DFA-ENTAccuracy69.2Unverified
3DFA-SAFNAccuracy69.1Unverified
4EasyTLAccuracy63.3Unverified
5MEDAAccuracy60.3Unverified
#ModelMetricClaimedVerifiedStatus
1CNN10-20% Mask PSNR3.23Unverified
#ModelMetricClaimedVerifiedStatus
1Chatterjee, Dutta et al.[1]Accuracy96.12Unverified
#ModelMetricClaimedVerifiedStatus
1Co-TuningAccuracy85.65Unverified
#ModelMetricClaimedVerifiedStatus
1Physical AccessEER5.74Unverified
#ModelMetricClaimedVerifiedStatus
1riadd.aucmediAUROC0.95Unverified