Luo Shi, Li Xiongfei, Zhang Xiaoli
Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012 China.
College of Computer Science and Technology, Jilin University, Changchun, 130012 China.
Multimed Tools Appl. 2023;82(7):10535-10552. doi: 10.1007/s11042-022-13667-5. Epub 2022 Sep 6.
Recently, anchor-based methods have achieved great progress in face detection. They adopt standard anchor matching strategy to sample positive anchors according to predefined IoU threshold. However, the max IoUs of extreme aspect ratio faces are still lower than fixed positive threshold, leading to the sampling failure from these faces. To construct a more robust detection model, more positive anchors from extreme aspect ratio faces need to be sampled and participate in the training phase. The goal of the present research is to improve the detection performance by reasonably extending sampling range of face aspect ratio. In this paper, we firstly explore the factors that affect the max IoU of each face in theory. Then, anchor matching simulation is performed to evaluate the sampling range of face aspect ratio. Finally, we propose a Wide Aspect Ratio Matching (WARM) strategy to collect more representative positive anchors from ground-truth faces across a wide range of aspect ratios. Besides, we present a novel feature enhancement module, named Receptive Field Diversity (RFD) module, to provide diverse receptive field corresponding to different aspect ratios. Extensive experiments have been conducted on popular benchmarks to show the effectiveness of our method, which can help detectors better capture extreme aspect ratio faces. Our method achieves promising APs on WIDER FACE validation dataset (easy: 0.965, medium: 0.955, hard: 0.904) and impressive generalization capability on FDDB dataset.
最近，基于锚点的方法在人脸检测方面取得了巨大进展。它们采用标准的锚点匹配策略，根据预定义的交并比（IoU）阈值对正锚点进行采样。然而，极端宽高比人脸的最大IoU仍然低于固定的正阈值，导致这些人脸采样失败。为了构建一个更强大的检测模型，需要从极端宽高比人脸中采样更多的正锚点并参与训练阶段。本研究的目标是通过合理扩展人脸宽高比的采样范围来提高检测性能。在本文中，我们首先从理论上探索影响每个人脸最大IoU的因素。然后，进行锚点匹配模拟以评估人脸宽高比的采样范围。最后，我们提出了一种宽高比匹配（WARM）策略，以从各种宽高比的真实人脸中收集更具代表性的正锚点。此外，我们提出了一种新颖的特征增强模块，称为感受野多样性（RFD）模块，以提供对应于不同宽高比的多样化感受野。我们在流行的基准上进行了大量实验，以证明我们方法的有效性，该方法可以帮助检测器更好地捕捉极端宽高比的人脸。我们的方法在WIDER FACE验证数据集上取得了可观的平均精度（AP）（简单：0.965，中等：0.955，困难：0.904），并且在FDDB数据集上具有令人印象深刻的泛化能力。
