Pushing the Limits of Unconstrained Face Detection: a Challenge Dataset and Baseline Results

Face detection has witnessed immense progress in the last few years, with new milestones being surpassed every year. While many challenges such as large variations in scale, pose, appearance are successfully addressed, there still exist several issues which are not specifically captured by existing methods or datasets. In this work, we identify the next set of challenges that requires attention from the research community and collect a new dataset of face images that involve these issues such as weather-based degradations, motion blur, focus blur and several others. We demonstrate that there is a considerable gap in the performance of state-of-the-art detectors and real-world requirements. Hence, in an attempt to fuel further research in unconstrained face detection, we present a new annotated Unconstrained Face Detection Dataset (UFDD) with several challenges and benchmark recent methods. Additionally, we provide an in-depth analysis of the results and failure cases of these methods. The UFDD dataset as well as baseline results, evaluation code and image source are available at: www.ufdd.info/.

1. Introduction

Face detection is the most important pre-processing step for many facial analysis tasks such as landmark detection [20], [55], face alignment [51], [43], [32], face recognition [30], face synthesis [42], [10], etc. The accuracy of face detection systems has a direct impact on these tasks and hence, the success of face detection is of crucial importance. Various challenges such as variations in pose, scale, illumination changes, variety of facial expressions, occlusion, etc., have to be addressed while building face detection algorithms. The success of Viola Jones face detector [40] enabled widespread usage of face detection in a variety of consumer devices and security systems.