Text Attention and Focal Negative Loss for Scene Text Detection | |
Huang Randong1,2; Xu Bo2 | |
2019-07 | |
会议日期 | 14-19 July 2019 |
会议地点 | Budapest, Hungary. |
英文摘要 | This paper proposes a novel attention mechanism and a fancy loss function for scene text detectors. Specifically, the attention mechanism can effectively identify the text regions by learning an attention mask automatically. The fine-grained attention mask is directly incorporated into the convolutional feature maps of a neural network to produce graininess-aware feature maps, which essentially obstruct the background inference and especially emphasize the text regions. Therefore, our graininess-aware feature maps concentrate on text regions, in especial those of exceedingly small size. Additionally, to address the extreme text-background class imbalance during training, we also propose a newfangled loss function, named Focal Negative Loss (FNL). The proposed loss function is able to down-weight the loss assigned to easy negative samples. Consequently, the proposed FNL can make training focused on hard negative samples. To evaluate the effectiveness of our text attention module and FNL, we integrate them into the efficient and accurate scene text detector (EAST). The comprehensive experimental results demonstrate that our text attention module and FNL can increase the performance of EAST by F-score of 3.98% on ICDAR2015 dataset and 1.87% on MSRA-TD500 dataset. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44562] |
专题 | 数字内容技术与服务研究中心_听觉模型与认知计算 |
通讯作者 | Xu Bo |
作者单位 | 1.University of Chinese Academy of Sciences, Beijing, China 2.Institute of Automation, Chinese Academy of Sciences, Beijing, China |
推荐引用方式 GB/T 7714 | Huang Randong,Xu Bo. Text Attention and Focal Negative Loss for Scene Text Detection[C]. 见:. Budapest, Hungary.. 14-19 July 2019. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论