用分布式卷积网络检测物体，多尺度特征融合提升精度。
Object Detection Based on Distributed Convolutional Neural Networks
- 通过多尺度特征检测，基于正向单调性定位目标区域。
- 仅需中心标注图像即可训练，支持并行检测多个类别。
- 轻量模型加速单目标检测，适合实时应用。
基于分布式卷积神经网络（DisCNN），提出一种直接的物体检测方法。DisCNN输出向量中特定正类的模块值随正类特征出现概率呈正单调性。因此，通过识别所有尺度下的高分块，并将其重叠形成边界框，即可实现正类物体的检测。核心思想是：在从具体子特征到抽象组合特征的多尺度上检测物体特征。训练DisCNN仅需带正负标签的物体中心图像数据。多正类检测可并行执行，显著加速；同时因模型轻量化，单物体检测也更快。
原文摘要 · Abstract (English)
Based on the Distributed Convolutional Neural Network(DisCNN), a straightforward object detection method is proposed. The modules of the output vector of a DisCNN with respect to a specific positive class are positively monotonic with the presence probabilities of the positive features. So, by identifying all high-scoring patches across all possible scales, the positive object can be detected by overlapping them to form a bounding box. The essential idea is that the object is detected by detecting its features on multiple scales, ranging from specific sub-features to abstract features composed of these sub-features. Training DisCNN requires only object-centered image data with positive and negative class labels. The detection process for multiple positive classes can be conducted in parallel to significantly accelerate it, and also faster for single-object detection because of its lightweight model architecture.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。