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

TL;DR

This paper introduces a new challenging face detection dataset called UFDD, highlighting the gaps in current methods under real-world conditions like weather and motion blur, and provides baseline results for future research.

Contribution

The paper presents the UFDD dataset with diverse real-world challenges and benchmarks recent face detection methods to identify their limitations.

Findings

Significant performance gap of state-of-the-art detectors on UFDD

Analysis of failure cases reveals key challenges in unconstrained face detection

Baseline results establish a benchmark for future research

Abstract

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 dataset as well as baseline results will be made publicly available in due time. The UFDD dataset as well as baseline results are available at: www.ufdd.info/