About

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

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Subtasks

Latest papers with code

Effect of Deep Transfer and Multi task Learning on Sperm Abnormality Detection

21 Nov 2021amirabbasii/Effect-of-Deep-Transfer-and-Multi-task-Learning-on-Sperm-Abnormality-Detection

Moreover, this is the first time that the concept of multi-task learning has been introduced to the field of Sperm Morphology Analysis (SMA).

ANOMALY DETECTION MULTI-TASK LEARNING

3
21 Nov 2021

Deep Transfer Learning Baselines for Sentiment Analysis in Russian

1 Jul 2021sismetanin/sentiment-analysis-in-russian

Firstly, we identified the most used publicly available sentiment analysis datasets in Russian and recent language models which officially support the Russian language.

SENTIMENT ANALYSIS TRANSFER LEARNING

12
01 Jul 2021

MRCBert: A Machine Reading ComprehensionApproach for Unsupervised Summarization

1 May 2021saurabhhssaurabh/reviews_summarization

We demonstrated our results on reviews of a product from the Electronics category in the Amazon Reviews dataset.

DECISION MAKING MACHINE READING COMPREHENSION TRANSFER LEARNING

0
01 May 2021

Determining Chess Game State From an Image

30 Apr 2021georgw777/chesscog

Identifying the configuration of chess pieces from an image of a chessboard is a problem in computer vision that has not yet been solved accurately.

TRANSFER LEARNING

9
30 Apr 2021

MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains

28 Apr 2021yaxingwang/MineGAN

Therefore, we propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain, either from a single or multiple pretrained GANs.

TRANSFER LEARNING

48
28 Apr 2021

Interpretable Embedding Procedure Knowledge Transfer via Stacked Principal Component Analysis and Graph Neural Network

28 Apr 2021sseung0703/IEPKT

Knowledge distillation (KD) is one of the most useful techniques for light-weight neural networks.

KNOWLEDGE DISTILLATION TRANSFER LEARNING

2
28 Apr 2021

Evaluating the Values of Sources in Transfer Learning

26 Apr 2021rizwan09/NLPDV

Transfer learning that adapts a model trained on data-rich sources to low-resource targets has been widely applied in natural language processing (NLP).

TRANSFER LEARNING

1
26 Apr 2021

Deep Learning Based Assessment of Synthetic Speech Naturalness

23 Apr 2021gabrielmittag/NISQA

Further, we show that the reliability of deep learning-based naturalness prediction can be improved by transfer learning from speech quality prediction models that are trained on objective POLQA scores.

SPEECH QUALITY SPEECH SYNTHESIS TRANSFER LEARNING VOICE CONVERSION

84
23 Apr 2021

DeepSpectrumLite: A Power-Efficient Transfer Learning Framework for Embedded Speech and Audio Processing from Decentralised Data

23 Apr 2021DeepSpectrum/DeepSpectrumLite

By obtaining state-of-the-art results on a set of paralinguistics tasks, we demonstrate the suitability of the proposed transfer learning approach for embedded audio signal processing, even when data is scarce.

TRANSFER LEARNING

3
23 Apr 2021

NanoNet: Real-Time Polyp Segmentation in Video Capsule Endoscopy and Colonoscopy

22 Apr 2021DebeshJha/NanoNet

To utilize automated methods in clinical settings, it is crucial to design lightweight models with low latency such that they can be integrated with low-end endoscope hardware devices.

COLORECTAL POLYPS CHARACTERIZATION INSTRUMENT RECOGNITION MEDICAL IMAGE SEGMENTATION REAL-TIME SEMANTIC SEGMENTATION TRANSFER LEARNING

3
22 Apr 2021