一个具有可变形卷积的路径聚合网络,用于视觉对象检测
Chengming Rao1,2, Zunhao Hu3, QiMing Zhao2
1College of Internet of Things Technology, Wuxi Institute of Technology, Wuxi, Jiangsu, China.
PeerJ. Computer science
|September 24, 2025
概括
本研究介绍了可变形卷积和路径聚合网络 (DePAN),以改进多尺度物体检测. DePAN有效地融合了功能,增强了单阶段探测器,以便更好地适用于现实世界.
科学领域:
- 计算机视觉 计算机视觉
- 深度学习 (Deep Learning) 是一种深度学习.
- 人工智能的人工智能
背景情况:
- 对象检测面临的挑战是多尺度对象.
- 现有的多尺度特征融合方法存在局限性.
研究的目的:
- 提出一个新的网络部,DePAN,用于单阶段物体探测器中有效的多尺度特征融合.
- 为了提高特征点采样使用可变形卷曲的灵活性.
主要方法:
- 介绍了可变形卷积和路径聚合网络 (DePAN).
- 在路径聚合网络的特征融合分支中集成了一个可变形的卷积块.
- 通过堆叠可变形卷积细胞来实现可变形卷积块.
- 将DePAN应用于Yolov6-N和YOLOV6-T基线模型.
主要成果:
- 德潘证明了多尺度特征的有效融合.
- 拟议的子提高了COCO2017和PASCAL VOC2012数据集的性能.
- 在医学图像数据集上也验证了有效性.
结论:
- DePAN 子显著增强了单阶段物体探测器.
- DePAN提供了灵活性,可以很容易地应用于各种物体检测模型.
- 该方法被证明是有效的,适用于现实世界的物体检测任务.
相关概念视频
Visual Agnosia
974
Visual agnosia is a condition characterized by the inability to recognize visually presented objects despite having normal vision. For instance, a person with visual agnosia can describe the shape and color of an object but cannot identify or name it. This impairment does not affect their visual field, acuity, color vision, brightness discrimination, language, or memory. An example of this condition in a social setting is someone at a dinner party asking for "that silver thing with a round...
974
Deconvolution
545
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
545

