DeepAI AI Chat
Log In Sign Up

Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark

by   Shuhao Qiu, et al.
Beijing University of Posts and Telecommunications

In recent years, deep learning-based methods have shown promising results in computer vision area. However, a common deep learning model requires a large amount of labeled data, which is labor-intensive to collect and label. What's more, the model can be ruined due to the domain shift between training data and testing data. Text recognition is a broadly studied field in computer vision and suffers from the same problems noted above due to the diversity of fonts and complicated backgrounds. In this paper, we focus on the text recognition problem and mainly make three contributions toward these problems. First, we collect a multi-source domain adaptation dataset for text recognition, including five different domains with over five million images, which is the first multi-domain text recognition dataset to our best knowledge. Secondly, we propose a new method called Meta Self-Learning, which combines the self-learning method with the meta-learning paradigm and achieves a better recognition result under the scene of multi-domain adaptation. Thirdly, extensive experiments are conducted on the dataset to provide a benchmark and also show the effectiveness of our method. The code of our work and dataset are available soon at


Moment Matching for Multi-Source Domain Adaptation

Conventional unsupervised domain adaptation (UDA) assumes that training ...

Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation

Conventional unsupervised domain adaptation (UDA) studies the knowledge ...

Adversarial Domain Adaptation for Stance Detection

This paper studies the problem of stance detection which aims to predict...

GeoNet: Benchmarking Unsupervised Adaptation across Geographies

In recent years, several efforts have been aimed at improving the robust...

Meta-Tsallis-Entropy Minimization: A New Self-Training Approach for Domain Adaptation on Text Classification

Text classification is a fundamental task for natural language processin...

Exploring Domain Shift in Extractive Text Summarization

Although domain shift has been well explored in many NLP applications, i...

The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs

The cross-depiction problem is that of recognising visual objects regard...

Code Repositories


Meta Self-learning for Multi-Source Domain Adaptation: A Benchmark

view repo