论文标题
ASFD：自动且可扩展的面部检测器
ASFD: Automatic and Scalable Face Detector
论文作者
论文摘要
除了当前的基于多尺度的检测器外，特征聚集和增强（FAE）模块还显示了尖端对象检测的性能提高。但是，这些手工制作的FAE模块在面部检测时显示出不一致的改善，这主要是由于其训练和应用语料库之间的分布差异很大，可可与较宽的面部。为了解决这个问题，我们从本质上分析了数据分布的效果，因此建议搜索有效的FAE体系结构，该架构称为Autofae，该搜索以相当大的利润来优于所有现有的FAE模块。在发现的Autofae和现有骨架上，将进一步构建和训练超级网，该超网自动在不同的复杂性约束下自动获得探测器家族。在流行的基准测试，较宽的脸部和FDDB上进行的广泛实验表明，提议的自动且可扩展的面部探测器（ASFD）家族的最先进的性能效率折衷。特别是，我们强大的ASFD-D6在更广泛的面部测试中优于AP 96.7/96.2/92.1的最佳竞争对手，而轻量级的ASFD-D0在带有VGA分辨率图像的V100 GPU上，轻巧的ASFD-D0的价格约为3.1 ms，超过320 fps。
Along with current multi-scale based detectors, Feature Aggregation and Enhancement (FAE) modules have shown superior performance gains for cutting-edge object detection. However, these hand-crafted FAE modules show inconsistent improvements on face detection, which is mainly due to the significant distribution difference between its training and applying corpus, COCO vs. WIDER Face. To tackle this problem, we essentially analyse the effect of data distribution, and consequently propose to search an effective FAE architecture, termed AutoFAE by a differentiable architecture search, which outperforms all existing FAE modules in face detection with a considerable margin. Upon the found AutoFAE and existing backbones, a supernet is further built and trained, which automatically obtains a family of detectors under the different complexity constraints. Extensive experiments conducted on popular benchmarks, WIDER Face and FDDB, demonstrate the state-of-the-art performance-efficiency trade-off for the proposed automatic and scalable face detector (ASFD) family. In particular, our strong ASFD-D6 outperforms the best competitor with AP 96.7/96.2/92.1 on WIDER Face test, and the lightweight ASFD-D0 costs about 3.1 ms, more than 320 FPS, on the V100 GPU with VGA-resolution images.
