Detector-in-Detector: Multi-Level Analysis for Human-Parts
This work addresses multi-level object detection for human parts, which is incremental as it builds on region-based detection methods with a novel two-detector framework.
The paper tackles the problem of detecting human bodies and their parts (hands, faces) by proposing a Detector-in-Detector network that leverages inherent correlations between body and parts in a coarse-to-fine manner, achieving excellent performance on a new dataset with 14,962 images and 106,879 annotations.
Vision-based person, hand or face detection approaches have achieved incredible success in recent years with the development of deep convolutional neural network (CNN). In this paper, we take the inherent correlation between the body and body parts into account and propose a new framework to boost up the detection performance of the multi-level objects. In particular, we adopt a region-based object detection structure with two carefully designed detectors to separately pay attention to the human body and body parts in a coarse-to-fine manner, which we call Detector-in-Detector network (DID-Net). The first detector is designed to detect human body, hand, and face. The second detector, based on the body detection results of the first detector, mainly focus on the detection of small hand and face inside each body. The framework is trained in an end-to-end way by optimizing a multi-task loss. Due to the lack of human body, face and hand detection dataset, we have collected and labeled a new large dataset named Human-Parts with 14,962 images and 106,879 annotations. Experiments show that our method can achieve excellent performance on Human-Parts.