# Robust Face Detection via Learning Small Faces on Hard Images

arXiv: https://arxiv.org/abs/1811.11662 · HTML: https://mlsanity.com/paper/1811.11662/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2018.

## Built on by (most cited first, 9 of 9)

- [HLA-Face: Joint High-Low Adaptation for Low Light Face Detection](https://mlsanity.com/paper/2104.01984/) (2021)
- [Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation](https://mlsanity.com/paper/2312.01220/) (2023)
- [Video Crowd Localization with Multi-focus Gaussian Neighborhood Attention and a Large-Scale Benchmark](https://mlsanity.com/paper/2107.08645/) (2021)
- [Going Deeper Into Face Detection: A Survey](https://mlsanity.com/paper/2103.14983/) (2021)
- [Detect Faces Efficiently: A Survey and Evaluations](https://mlsanity.com/paper/2112.01787/) (2021)
- [Rethinking the backbone architecture for tiny object detection](https://mlsanity.com/paper/2303.11267/) (2023)
- [GroupGazer: A Tool to Compute the Gaze per Participant in Groups with integrated Calibration to Map the Gaze Online to a Screen or Beamer Projection](https://mlsanity.com/paper/2201.07692/) (2022)
- [The Importance of Anti-Aliasing in Tiny Object Detection](https://mlsanity.com/paper/2310.14221/) (2023)
- [Archival Faces: Detection of Faces in Digitized Historical Documents](https://mlsanity.com/paper/2504.00558/) (2025)

## Abstract (arXiv)

Recent anchor-based deep face detectors have achieved promising performance, but they are still struggling to detect hard faces, such as small, blurred and partially occluded faces. A reason is that they treat all images and faces equally, without putting more effort on hard ones; however, many training images only contain easy faces, which are less helpful to achieve better performance on hard images. In this paper, we propose that the robustness of a face detector against hard faces can be improved by learning small faces on hard images. Our intuitions are (1) hard images are the images which contain at least one hard face, thus they facilitate training robust face detectors; (2) most hard faces are small faces and other types of hard faces can be easily converted to small faces by shrinking. We build an anchor-based deep face detector, which only output a single feature map with small anchors, to specifically learn small faces and train it by a novel hard image mining strategy. Extensive experiments have been conducted on WIDER FACE, FDDB, Pascal Faces, and AFW datasets to show the effectiveness of our method. Our method achieves APs of 95.7, 94.9 and 89.7 on easy, medium and hard WIDER FACE val dataset respectively, which surpass the previous state-of-the-arts, especially on the hard subset. Code and model are available at https://github.com/bairdzhang/smallhardface.