Browse SoTA > Methodology > Transfer Learning

Transfer Learning

567 papers with code ยท Methodology

Transfer learning is a methodology where weights from a model trained on one task are taken and either used (a) to construct a fixed feature extractor, (b) as weight initialization and/or fine-tuning.

( Image credit: Subodh Malgonde )

Benchmarks

Latest papers without code

Improving the Accuracy of Global Forecasting Models using Time Series Data Augmentation

6 Aug 2020

Forecasting models that are trained across sets of many time series, known as Global Forecasting Models (GFM), have shown recently promising results in forecasting competitions and real-world applications, outperforming many state-of-the-art univariate forecasting techniques.

DATA AUGMENTATION TIME SERIES TRANSFER LEARNING

Federated Transfer Learning with Dynamic Gradient Aggregation

6 Aug 2020

The target scenario is Acoustic Model training based on this platform.

SPEECH RECOGNITION TRANSFER LEARNING

A Novel Method For Designing Transferable Soft Sensors And Its Application

5 Aug 2020

In this paper, a new approach is proposed for designing transferable soft sensors.

TRANSFER LEARNING

Duality Diagram Similarity: a generic framework for initialization selection in task transfer learning

5 Aug 2020

In this paper, we tackle an open research question in transfer learning, which is selecting a model initialization to achieve high performance on a new task, given several pre-trained models.

MODEL SELECTION SEMANTIC SEGMENTATION TRANSFER LEARNING

MultiCheXNet: A Multi-Task Learning Deep Network For Pneumonia-like Diseases Diagnosis From X-ray Scans

5 Aug 2020

The common encoder in our architecture can capture useful common features present in the different tasks.

MULTI-TASK LEARNING

Prompt Agnostic Essay Scorer: A Domain Generalization Approach to Cross-prompt Automated Essay Scoring

4 Aug 2020

Cross-prompt automated essay scoring (AES) requires the system to use non target-prompt essays to award scores to a target-prompt essay.

AUTOMATED ESSAY SCORING DOMAIN GENERALIZATION TRANSFER LEARNING

Memory Efficient Class-Incremental Learning for Image Classification

4 Aug 2020

To cope with the forgetting problem, many CIL methods transfer the knowledge of old classes by preserving some exemplar samples into the size-constrained memory buffer.

IMAGE CLASSIFICATION INCREMENTAL LEARNING TRANSFER LEARNING

Online Few-shot Gesture Learning on a Neuromorphic Processor

3 Aug 2020

Using gesturerecognition as a case study, we show SOEL can be used for onlinefew-shot learning of new classes of pre-recorded gesture data andrapid online learning of new gestures from data streamed livefrom a Dynamic Active-pixel Vision Sensor to an Intel Loihineuromorphic research processor.

TRANSFER LEARNING

A Foliated View of Transfer Learning

2 Aug 2020

Transfer learning considers a learning process where a new task is solved by transferring relevant knowledge from known solutions to related tasks.

TRANSFER LEARNING

An Explainable Machine Learning Model for Early Detection of Parkinson's Disease using LIME on DaTscan Imagery

1 Aug 2020

Keeping model interpretability of paramount importance, especially in the healthcare field, this study utilises LIME explanations to distinguish PD from non-PD, using visual superpixels on the DaTscans.

TRANSFER LEARNING