提升小目标检测性能，通过高频与空间感知增强特征
HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection
- 引入高频感知模块，用高通滤波生成掩码权重
- 在AI-TOD数据集上优于现有模型，显著提升小目标识别率
- 适合需要精准检测小物体的工业或遥感场景
特征金字塔网络（FPN）虽显著提升了目标检测性能，但在检测小目标时仍面临挑战，因其特征在特征图中占比极小。尽管FPN融合多尺度特征，却未直接增强或丰富小目标特征，且缺乏空间感知能力。为此，本文提出一种新型高频率与空间感知特征金字塔网络（HS-FPN），包含两个创新模块：首先设计高频感知模块（HFP），通过高通滤波生成高频响应，作为空间与通道维度的掩码权重，以增强并突出原始特征图中的小目标特征；其次开发空间依赖感知模块（SDP），捕捉FPN缺失的空间依赖关系。实验表明，在AI-TOD数据集上，基于HS-FPN的检测器相较于当前最优模型展现出显著优势。
原文摘要 · Abstract (English)
The introduction of Feature Pyramid Network (FPN) has significantly improved object detection performance. However, substantial challenges remain in detecting tiny objects, as their features occupy only a very small proportion of the feature maps. Although FPN integrates multi-scale features, it does not directly enhance or enrich the features of tiny objects. Furthermore, FPN lacks spatial perception ability. To address these issues, we propose a novel High Frequency and Spatial Perception Feature Pyramid Network (HS-FPN) with two innovative modules. First, we designed a high frequency perception module (HFP) that generates high frequency responses through high pass filters. These high frequency responses are used as mask weights from both spatial and channel perspectives to enrich and highlight the features of tiny objects in the original feature maps. Second, we developed a spatial dependency perception module (SDP) to capture the spatial dependencies that FPN lacks. Our experiments demonstrate that detectors based on HS-FPN exhibit competitive advantages over state-of-the-art models on the AI-TOD dataset for tiny object detection.
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。