Rethinking prediction alignment in one-stage object detection
文献类型：期刊论文
| 作者 | Xiao, Junrui1,2 ; Jiang, He1,2; Li, Zhikai1,2; Gu, Qingyi1
|
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2022-12-01 |
| 卷号 | 514页码:58-69 |
| 关键词 | Deep learning Object detection Detection head Label assignment |
| ISSN号 | 0925-2312 |
| DOI | 10.1016/j.neucom.2022.09.132 |
| 通讯作者 | Gu, Qingyi(qingyi.gu@ia.ac.cn) |
| 英文摘要 | Owing to their excellent performance and efficiency, one-stage detectors have been widely used in mul-timedia tasks, such as temporal action detection, object tracking, and video detection. However, misalign-ment between classification and regression branches limits the accuracy of the detector. Most existing works add an auxiliary branch or adopt a specific sample assignment strategy to alleviate this problem, but with little effect. In this paper, we attribute this to incomplete branch interactions and propose a comprehensive Predictive Aligned Object Detector (PAOD), which can better correlate two subtasks. Specifically, our proposed PAOD achieves a better trade-off between prediction-interactive and prediction-specific by adopting an Iterative Aggregation Module (IAM) and a Mutual Constraint Module (MCM). We also design an aligned label assignment with an adaptive metric and re-weighting mechanism to further narrow the misalignment between prediction heads. With negligible additional overhead, PAOD achieves 50.4 AP at single-model single-scale testing on the MS-COCO branch, which demonstrates the effectiveness of our proposal. Notably, PAOD consistently outperforms previous sota such as ATSS (47.7 AP), BorderDet (48.0 AP) and GFL (48.2 AP) by a large margin on COCO test-dev data -set, and achieves better performance than various dense detectors on Pascal VOC and CrowdHuman data -sets. Code is available at https://github.com/JunruiXiao/PAOD.(c) 2022 Elsevier B.V. All rights reserved. |
| 资助项目 | Scientific Instrument Developing Project of the Chinese Academy of Sciences ; [YJKYYQ20200045] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000869405900004 |
| 出版者 | ELSEVIER |
| 资助机构 | Scientific Instrument Developing Project of the Chinese Academy of Sciences |
| 源URL | [http://ir.ia.ac.cn/handle/173211/50260]  |
| 专题 | 精密感知与控制研究中心_精密感知与控制 |
| 通讯作者 | Gu, Qingyi |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, East Zhongguancun Rd, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Jingjia Rd, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Xiao, Junrui,Jiang, He,Li, Zhikai,et al. Rethinking prediction alignment in one-stage object detection[J]. NEUROCOMPUTING,2022,514:58-69. |
| APA | Xiao, Junrui,Jiang, He,Li, Zhikai,&Gu, Qingyi.(2022).Rethinking prediction alignment in one-stage object detection.NEUROCOMPUTING,514,58-69. |
| MLA | Xiao, Junrui,et al."Rethinking prediction alignment in one-stage object detection".NEUROCOMPUTING 514(2022):58-69. |
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。