SODAR: Exploring Locally Aggregated Learning of Mask Representations for Instance Segmentation
文献类型：期刊论文
| 作者 | Wang, Tao1,2; Liew, Jun Hao3; Li, Yu4; Chen, Yunpeng5; Feng, Jiashi3 |
| 刊名 | IEEE TRANSACTIONS ON IMAGE PROCESSING
 |
| 出版日期 | 2022 |
| 卷号 | 31页码:839-851 |
| 关键词 | Computer architecture Microprocessors Image segmentation Convolution Predictive models Shape Computational modeling Instance segmentation object detection one-stage feature aggregation mask representation |
| ISSN号 | 1057-7149 |
| DOI | 10.1109/TIP.2021.3135717 |
| 英文摘要 | Recent state-of-the-art one-stage instance segmentation model SOLO divides the input image into a grid and directly predicts per grid cell object masks with fully-convolutional networks, yielding comparably good performance as traditional two-stage Mask R-CNN yet enjoying much simpler architecture and higher efficiency. We observe SOLO generates similar masks for an object at nearby grid cells, and these neighboring predictions can complement each other as some may better segment certain object part, most of which are however directly discarded by non-maximum-suppression. Motivated by the observed gap, we develop a novel learning-based aggregation method that improves upon SOLO by leveraging the rich neighboring information while maintaining the architectural efficiency. The resulting model is named SODAR. Unlike the original per grid cell object masks, SODAR is implicitly supervised to learn mask representations that encode geometric structure of nearby objects and complement adjacent representations with context. The aggregation method further includes two novel designs: 1) a mask interpolation mechanism that enables the model to generate much fewer mask representations by sharing neighboring representations among nearby grid cells, and thus saves computation and memory; 2) a deformable neighbour sampling mechanism that allows the model to adaptively adjust neighbor sampling locations thus gathering mask representations with more relevant context and achieving higher performance. SODAR significantly improves the instance segmentation performance, e.g., it outperforms a SOLO model with ResNet-101 backbone by 2.2 AP on COCO test set, with only about 3% additional computation. We further show consistent performance gain with the SOLOv2 model. |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000739632300004 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/18394]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Wang, Tao |
| 作者单位 | 1.Natl Univ Singapore, Grad Sch Integrat Sci & Engn, Singapore 119077, Singapore 2.Natl Univ Singapore, Inst Data Sci, Singapore 119077, Singapore 3.Natl Univ Singapore, Dept Elect & Comp Engn, Singapore 119077, Singapore 4.Chinese Acad Sci, Inst Comp Technol, Beijing 100049, Peoples R China 5.YITU Technol, Beijing 100086, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Tao,Liew, Jun Hao,Li, Yu,et al. SODAR: Exploring Locally Aggregated Learning of Mask Representations for Instance Segmentation[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2022,31:839-851. |
| APA | Wang, Tao,Liew, Jun Hao,Li, Yu,Chen, Yunpeng,&Feng, Jiashi.(2022).SODAR: Exploring Locally Aggregated Learning of Mask Representations for Instance Segmentation.IEEE TRANSACTIONS ON IMAGE PROCESSING,31,839-851. |
| MLA | Wang, Tao,et al."SODAR: Exploring Locally Aggregated Learning of Mask Representations for Instance Segmentation".IEEE TRANSACTIONS ON IMAGE PROCESSING 31(2022):839-851. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
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。