Faster RCNN has achieved great success for generic object detection including PASCAL object detection and MS COCO object detection. In this report, we propose a detailed designed Faster RCNN method named FDNet1.0 for face detection. Several techniques were employed including multi-scale training, multi-scale testing, light-designed RCNN, some tricks for inference and a vote-based ensemble method. Our method achieves two 1th places and one 2nd place in three tasks over WIDER FACE validation dataset (easy set, medium set, hard set).
翻译：更快的RCNN在普通物体探测方面取得了巨大成功,包括PASCAL物体探测和MS COCO物体探测。我们在本报告中提议了一种详细设计的名为FDNet1.0的更快的RCNN方法,用于面对面探测。我们采用了多种技术,包括多级培训、多级测试、简易设计的RCNN、一些推论技巧和基于投票的共用方法。我们的方法在WIDER FACE验证数据集(简易、中型、硬套)的三项任务中达到了两个第1位和第2位。我们的方法在WIDER FACE验证数据集(简易、中型、硬套)的三项任务中达到了两个第1位和第2位。
相关内容
微信扫码咨询专知VIP会员