- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Automatic Translation feature is available on CiNii Labs
- Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
Cascaded Multi-Channel Feature Fusion for Object Detection
-
- Lifei He
- Hangzhou Dianzi University and University of Yamanashi, China
-
- Ryutarou Ohbuchi
- University of Yamanashi
-
- Ming Jiang
- Hangzhou Dianzi University
-
- Takahiko Furuya
- University of Yamanashi
-
- Min Zhang
- Hangzhou Dianzi University
Description
In this paper, we propose and evaluate a novel object detection architecture called Cascaded Multi-Channel Feature Pyramid Network, or CM-FPN. The proposed network, which is based on Feature Pyramid Network by Lin et al., employs multi-stage cascaded top-down feature pyramid networks to extract more semantic multiresolution feature maps for object region proposal and object classification. Depths of the feature maps are adjusted so that the feature maps in the later stages of the cascades where they are more semantic have higher channel depths. Experimental evaluation of the proposed approach has shown that the proposed method produces higher object detection accuracy.
Journal
-
- 2020 the 3rd International Conference on Control and Computer Vision
-
2020 the 3rd International Conference on Control and Computer Vision 11-16, 2020-08-23
ACM
- Tweet
Details 詳細情報について
-
- CRID
- 1360572092493029120
-
- Article Type
- journal article
-
- Data Source
-
- Crossref
- KAKEN
- OpenAIRE
