.png){kind=icon}
返回
Weak supervision for generating pixel-level annotations in scene text segmentation
.png){kind=icon}
OA
AI
DOI：10.1016/j.patrec.2020.06.023.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Providing pixel-level supervisions for scene text segmentation is inherently difficult and costly, so that only few small datasets are available for this task. To face the scarcity of training data, previous approaches based on Convolutional Neural Networks (CNNs) rely on the use of a synthetic dataset for pretraining. However, synthetic data cannot reproduce the complexity and variability of natural images. In this work, we propose to use a weakly supervised learning approach to reduce the domain-shift between synthetic and real data. Leveraging the bounding-box supervision of the COCO-Text and the MLT datasets, we generate weak pixel-level supervisions of real images. In particular, the COCO-Text-Segmentation (COCO_TS) and the MLT-Segmentation (MLT_S) datasets are created and released. These two datasets are used to train a CNN, the Segmentation Multiscale Attention Network (SMANet), which is specifically designed to face some peculiarities of the scene text segmentation task. The SMANet is trained end-to-end on the proposed datasets, and the experiments show that COCO_TS and MLT_S are a valid alternative to synthetic images, allowing to use only a fraction of the training samples, with a significant improvement in performance. (C) 2020 Elsevier B.V. All rights reserved.
Keyword:
Image analysis
Image processing
Neural nets
Artificial intelligence
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.3
论文数:
8.0K
被引数:
1.6W
机构
引用论文
.png){kind=icon}
Exercise and Anxiety Reduction: Examination of Temperature as an Explanation for Affective Change
PREAI
分享收藏
查看更多内容