ASFD：自动可扩展人脸检测器
ASFD: Automatic and Scalable Face Detector
摘要：
与当前基于多尺度的检测器一起，特征聚合和增强（FAE）模块已经显示出用于尖端目标检测的优异性能增益。然而，这些手工制作的FAE模块在人脸检测方面表现出不一致的改进，这主要是由于其训练和应用语料库之间的显著分布差异，COCO与WIDER Face。为了解决这个问题，我们从根本上分析了数据分布的影响，并因此提出了搜索一个有效的FAE架构，称为AutoFAE的微分架构搜索，它优于所有现有的FAE模块在人脸检测有相当大的利润。在找到的AutoFAE和现有的骨干上，进一步构建和训练超网，该超网自动获得不同复杂度约束下的检测器族。广泛的实验进行流行的基准，WIDER脸和FDDB，展示了国家的最先进的性能效率的权衡所提出的自动和可扩展的人脸检测器（ASFD）的家庭。特别是，我们强大的ASFD-D 6在WIDER Face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-D 0在V100 GPU上的VGA分辨率图像成本约为3.1 ms，超过320 FPS。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
