MSFFAL: Few-Shot Object Detection via Multi-Scale Feature Fusion and Attentive Learning
文献类型：期刊论文
| 作者 | Zhang, Tianzhao1,4; Sun, Ruoxi1,3; Wan, Yong2; Zhang, Fuping1; Wei, Jianming1 |
| 刊名 | SENSORS
 |
| 出版日期 | 2023-04-01 |
| 卷号 | 23期号:7页码:- |
| 关键词 | few-shot object detection few-shot learning attention mechanism multi-scale feature fusion |
| 英文摘要 | Few-shot object detection (FSOD) is proposed to solve the application problem of traditional detectors in scenarios lacking training samples. The meta-learning methods have attracted the researchers' attention for their excellent generalization performance. They usually select the same class of support features according to the query labels to weight the query features. However, the model cannot possess the ability of active identification only by using the same category support features, and feature selection causes difficulties in the testing process without labels. The single-scale feature of the model also leads to poor performance in small object detection. In addition, the hard samples in the support branch impact the backbone's representation of the support features, thus impacting the feature weighting process. To overcome these problems, we propose a multi-scale feature fusion and attentive learning (MSFFAL) framework for few-shot object detection. We first design the backbone with multi-scale feature fusion and channel attention mechanism to improve the model's detection accuracy on small objects and the representation of hard support samples. Based on this, we propose an attention loss to replace the feature weighting module. The loss allows the model to consistently represent the objects of the same category in the two branches and realizes the active recognition of the model. The model no longer depends on query labels to select features when testing, optimizing the model testing process. The experiments show that MSFFAL outperforms the state-of-the-art (SOTA) by 0.7-7.8% on the Pascal VOC and exhibits 1.61 times the result of the baseline model in MS COCO's small objects detection. |
| 学科主题 | Chemistry ; Engineering ; Instruments & Instrumentation |
| 语种 | 英语 |
| WOS记录号 | WOS:000969003700001 |
| 出版者 | MDPI |
| 源URL | [http://119.78.100.198/handle/2S6PX9GI/35275]  |
| 专题 | 中科院武汉岩土力学所 |
| 作者单位 | 1.Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China 2.State Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan 430071, China 3.School of Information Science and Technology, ShanghaiTech University, Shanghai 201210, China 4.School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China |
| 推荐引用方式 GB/T 7714 | Zhang, Tianzhao,Sun, Ruoxi,Wan, Yong,et al. MSFFAL: Few-Shot Object Detection via Multi-Scale Feature Fusion and Attentive Learning[J]. SENSORS,2023,23(7):-. |
| APA | Zhang, Tianzhao,Sun, Ruoxi,Wan, Yong,Zhang, Fuping,&Wei, Jianming.(2023).MSFFAL: Few-Shot Object Detection via Multi-Scale Feature Fusion and Attentive Learning.SENSORS,23(7),-. |
| MLA | Zhang, Tianzhao,et al."MSFFAL: Few-Shot Object Detection via Multi-Scale Feature Fusion and Attentive Learning".SENSORS 23.7(2023):-. |
入库方式： OAI收割
来源：武汉岩土力学研究所
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。