Multi-Initialization Meta-Learning with Domain Adaptation

2021 ◽  
Author(s):  
Zhengyu Chen ◽  
Donglin Wang
Keyword(s):  
Domain Adaptation ◽  
Meta Learning

scholarly journals Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification

2021 ◽  
Author(s):  
Chengcheng Han ◽  
Zeqiu Fan ◽  
Dongxiang Zhang ◽  
Minghui Qiu ◽  
Ming Gao ◽  
...  
Keyword(s):  
Text Classification ◽  
Domain Adaptation ◽  
Meta Learning

scholarly journals Cross Domain Adaptation of Crowd Counting with Model-Agnostic Meta-Learning

2021 ◽  
Vol 11 (24) ◽  
pp. 12037
Author(s):  
Xiaoyu Hou ◽  
Jihui Xu ◽  
Jinming Wu ◽  
Huaiyu Xu
Keyword(s):  
Feature Extraction ◽  
Supervised Learning ◽  
Density Estimation ◽  
Real World ◽  
Domain Adaptation ◽  
Manual Annotation ◽  
Crowd Counting ◽  
Cross Domain ◽  
Meta Learning ◽  
Density Map

Counting people in crowd scenarios is extensively conducted in drone inspections, video surveillance, and public safety applications. Today, crowd count algorithms with supervised learning have improved significantly, but with a reliance on a large amount of manual annotation. However, in real world scenarios, different photo angles, exposures, location heights, complex backgrounds, and limited annotation data lead to supervised learning methods not working satisfactorily, plus many of them suffer from overfitting problems. To address the above issues, we focus on training synthetic crowd data and investigate how to transfer information to real-world datasets while reducing the need for manual annotation. CNN-based crowd-counting algorithms usually consist of feature extraction, density estimation, and count regression. To improve the domain adaptation in feature extraction, we propose an adaptive domain-invariant feature extracting module. Meanwhile, after taking inspiration from recent innovative meta-learning, we present a dynamic-β MAML algorithm to generate a density map in unseen novel scenes and render the density estimation model more universal. Finally, we use a counting map refiner to optimize the coarse density map transformation into a fine density map and then regress the crowd number. Extensive experiments show that our proposed domain adaptation- and model-generalization methods can effectively suppress domain gaps and produce elaborate density maps in cross-domain crowd-counting scenarios. We demonstrate that the proposals in our paper outperform current state-of-the-art techniques.

Dynamic Tuning and Weighting of Meta-learning for NMT Domain Adaptation

2021 ◽  
pp. 576-587
Author(s):  
Ziyue Song ◽  
Zhiyuan Ma ◽  
Kaiyue Qi ◽  
Gongshen Liu
Keyword(s):  
Domain Adaptation ◽  
Dynamic Tuning ◽  
Meta Learning

Similarity-based meta-learning network with adversarial domain adaptation for cross-domain fault identification

2021 ◽  
Vol 217 ◽  
pp. 106829
Author(s):  
Yong Feng ◽  
Jinglong Chen ◽  
Zhuozheng Yang ◽  
Xiaogang Song ◽  
Yuanhong Chang ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
Fault Identification ◽  
Learning Network ◽  
Cross Domain ◽  
Meta Learning

scholarly journals MetaMT, a Meta Learning Method Leveraging Multiple Domain Data for Low Resource Machine Translation

2020 ◽  
Vol 34 (05) ◽  
pp. 8245-8252
Author(s):  
Rumeng Li ◽  
Xun Wang ◽  
Hong Yu
Keyword(s):  
Machine Translation ◽  
Domain Adaptation ◽  
Training Data ◽  
Model Parameters ◽  
Parallel Corpora ◽  
Training Strategy ◽  
Low Resource ◽  
Domain Specific ◽  
Representational Space ◽  
Meta Learning

Neural machine translation (NMT) models have achieved state-of-the-art translation quality with a large quantity of parallel corpora available. However, their performance suffers significantly when it comes to domain-specific translations, in which training data are usually scarce. In this paper, we present a novel NMT model with a new word embedding transition technique for fast domain adaption. We propose to split parameters in the model into two groups: model parameters and meta parameters. The former are used to model the translation while the latter are used to adjust the representational space to generalize the model to different domains. We mimic the domain adaptation of the machine translation model to low-resource domains using multiple translation tasks on different domains. A new training strategy based on meta-learning is developed along with the proposed model to update the model parameters and meta parameters alternately. Experiments on datasets of different domains showed substantial improvements of NMT performances on a limited amount of data.

scholarly journals Domain Adaptation for Medical Image Segmentation: A Meta-Learning Method

2021 ◽  
Vol 7 (2) ◽  
pp. 31
Author(s):  
Penghao Zhang ◽  
Jiayue Li ◽  
Yining Wang ◽  
Judong Pan
Keyword(s):  
Image Segmentation ◽  
Medical Image ◽  
Domain Adaptation ◽  
Medical Image Segmentation ◽  
Training Data ◽  
Tissue Type ◽  
Dice Similarity Coefficient ◽  
Learning Method ◽  
Task Distribution ◽  
Meta Learning

Convolutional neural networks (CNNs) have demonstrated great achievement in increasing the accuracy and stability of medical image segmentation. However, existing CNNs are limited by the problem of dependency on the availability of training data owing to high manual annotation costs and privacy issues. To counter this limitation, domain adaptation (DA) and few-shot learning have been extensively studied. Inspired by these two categories of approaches, we propose an optimization-based meta-learning method for segmentation tasks. Even though existing meta-learning methods use prior knowledge to choose parameters that generalize well from few examples, these methods limit the diversity of the task distribution that they can learn from in medical image segmentation. In this paper, we propose a meta-learning algorithm to augment the existing algorithms with the capability to learn from diverse segmentation tasks across the entire task distribution. Specifically, our algorithm aims to learn from the diversity of image features which characterize a specific tissue type while showing diverse signal intensities. To demonstrate the effectiveness of the proposed algorithm, we conducted experiments using a diverse set of segmentation tasks from the Medical Segmentation Decathlon and two meta-learning benchmarks: model-agnostic meta-learning (MAML) and Reptile. U-Net and Dice similarity coefficient (DSC) were selected as the baseline model and the main performance metric, respectively. The experimental results show that our algorithm maximally surpasses MAML and Reptile by 2% and 2.4% respectively, in terms of the DSC. By showing a consistent improvement in subjective measures, we can also infer that our algorithm can produce a better generalization of a target task that has few examples.

Sign in / Sign up

Export Citation Format

Share Document