Browse > Methodology > Transfer Learning

Transfer Learning

260 papers with code · 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.

State-of-the-art leaderboards

Latest papers with code

VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation

18 Aug 2019shamanez/VUSFA-Variational-Universal-Successor-Features-Approximator

In this paper, we show how novel transfer reinforcement learning techniques can be applied to the complex task of target driven navigation using the photorealistic AI2THOR simulator.

TRANSFER REINFORCEMENT LEARNING VISUAL NAVIGATION

2
18 Aug 2019

Progressive Transfer Learning for Person Re-identification

7 Aug 2019ZJULearning/PTL

Model fine-tuning is a widely used transfer learning approach in person Re-identification (ReID) applications, which fine-tuning a pre-trained feature extraction model into the target scenario instead of training a model from scratch.

PERSON RE-IDENTIFICATION TRANSFER LEARNING

7
07 Aug 2019

A Survey on Deep Learning of Small Sample in Biomedical Image Analysis

1 Aug 2019PengyiZhang/MIADeepSSL

In order to accelerate the clinical usage of biomedical image analysis based on deep learning techniques, we intentionally expand this survey to include the explanation methods for deep models that are important to clinical decision making.

ACTIVE LEARNING DATA AUGMENTATION DECISION MAKING TRANSFER LEARNING

9
01 Aug 2019

hULMonA: The Universal Language Model in Arabic

WS 2019 aub-mind/hULMonA

Experiment results show that the developed hULMonA and multi-lingual ULM are able to generalize well to multiple Arabic data sets and achieve new state of the art results in Arabic Sentiment Analysis for some of the tested sets.

ARABIC SENTIMENT ANALYSIS LANGUAGE MODELLING TEXT CLASSIFICATION TRANSFER LEARNING

6
01 Aug 2019

Towards More Accurate Automatic Sleep Staging via Deep Transfer Learning

30 Jul 2019pquochuy/sleep_transfer_learning

This work presents a deep transfer learning approach to overcome the channel mismatch problem and enable transferring knowledge from a large dataset to a small cohort for automatic sleep staging.

TRANSFER LEARNING

8
30 Jul 2019

Zero-shot transfer for implicit discourse relation classification

30 Jul 2019MurathanKurfali/multilingual_IDRC

Automatically classifying the relation between sentences in a discourse is a challenging task, in particular when there is no overt expression of the relation.

IMPLICIT DISCOURSE RELATION CLASSIFICATION TRANSFER LEARNING

0
30 Jul 2019

Learnable Parameter Similarity

27 Jul 2019Wanggcong/learnable-parameter-similarity

Most of the existing approaches focus on specific visual tasks while ignoring the relations between them.

TRANSFER LEARNING

2
27 Jul 2019

Automatic Grading of Individual Knee Osteoarthritis Features in Plain Radiographs using Deep Convolutional Neural Networks

18 Jul 2019MIPT-Oulu/solt

Knee osteoarthritis (OA) is the most common musculoskeletal disease in the world.

TRANSFER LEARNING

141
18 Jul 2019

LakhNES: Improving multi-instrumental music generation with cross-domain pre-training

10 Jul 2019chrisdonahue/LakhNES

We are interested in the task of generating multi-instrumental music scores.

MUSIC GENERATION TRANSFER LEARNING

86
10 Jul 2019

Personalised aesthetics with residual adapters

In Iberian Conference on Pattern Recognition and Image Analysis 2019 crp94/Personalised-aesthetic-assessment-using-residual-adapters

The use of computational methods to evaluate aesthetics in photography has gained interest in recent years due to the popularization of convolutional neural networks and the availability of new annotated datasets.

IMAGE QUALITY ASSESSMENT IMAGE QUALITY ESTIMATION RECOMMENDATION SYSTEMS TRANSFER LEARNING

7
10 Jul 2019