Adaptive Long-Neck Network With Atrous-Residual Structure for Instance Segmentation
文献类型：期刊论文
| 作者 | Geng, Wenjie1,2 ; Cao, Zhiqiang1,2; Guan, Peiyu1,2; Ren, Guangli1,2; Yu, Junzhi3; Jing, Fengshui1,2
|
| 刊名 | IEEE SENSORS JOURNAL
 |
| 出版日期 | 2023-04-01 |
| 卷号 | 23期号:7页码:7786-7797 |
| 关键词 | Adaptive long-neck (ALN) network atrous-residual structure instance segmentation |
| ISSN号 | 1530-437X |
| DOI | 10.1109/JSEN.2023.3244818 |
| 通讯作者 | Cao, Zhiqiang(zhiqiang.cao@ia.ac.cn) |
| 英文摘要 | Instance segmentation is an important yet challenging task in the computer vision field. Existing mainstream single-stage solution with parameterized mask representation has designed the neck models to fuse features of different layers; however, the performance of instance segmentation is still restricted to the layer-by-layer transmission scheme. In this article, an instance segmentation framework with an adaptive long-neck (ALN) network and atrous-residual structure is proposed. The long-neck network is composed of two bidirectional fusion units, which are cascaded to facilitate the information communication among features of different layers in top-down and bottom-up pathways. In particular, a new cross-layer transmission scheme is introduced in a top-down pathway to achieve a hybrid dense fusion of multiscale features and weights of different features are learned adaptively according to their respective contributions to promote the network convergence. Meanwhile, a bottom-up pathway further complements the features with more location clues. In this way, high-level semantic information and low-level location information are tightly integrated. Furthermore, an atrous-residual structure is added to the mask prototype branch of instance prediction to capture more contextual information. This contributes to the generation of high-quality masks. The experimental results indicate that the proposed method achieves effective segmentation and the outputted masks match the contours of objects. |
| 资助项目 | National Natural Science Foundation of China[62073322] ; National Natural Science Foundation of China[61633020] ; CIE-Tencent Robotics X Rhino-Bird Focused Research Program[2022-07] ; Beijing Natural Science Foundation[2022MQ05] |
| WOS研究方向 | Engineering ; Instruments & Instrumentation ; Physics |
| 语种 | 英语 |
| WOS记录号 | WOS:001011420400139 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China ; CIE-Tencent Robotics X Rhino-Bird Focused Research Program ; Beijing Natural Science Foundation |
| 源URL | [http://ir.ia.ac.cn/handle/173211/53849]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Cao, Zhiqiang |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Peking Univ, Dept Adv Mfg & Robot, Coll Engn, BIC ESAT, Beijing 100871, Peoples R China |
| 推荐引用方式 GB/T 7714 | Geng, Wenjie,Cao, Zhiqiang,Guan, Peiyu,et al. Adaptive Long-Neck Network With Atrous-Residual Structure for Instance Segmentation[J]. IEEE SENSORS JOURNAL,2023,23(7):7786-7797. |
| APA | Geng, Wenjie,Cao, Zhiqiang,Guan, Peiyu,Ren, Guangli,Yu, Junzhi,&Jing, Fengshui.(2023).Adaptive Long-Neck Network With Atrous-Residual Structure for Instance Segmentation.IEEE SENSORS JOURNAL,23(7),7786-7797. |
| MLA | Geng, Wenjie,et al."Adaptive Long-Neck Network With Atrous-Residual Structure for Instance Segmentation".IEEE SENSORS JOURNAL 23.7(2023):7786-7797. |
入库方式： OAI收割
来源：自动化研究所
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。