# EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse

arXiv: https://arxiv.org/abs/1906.06579 · HTML: https://mlsanity.com/paper/1906.06579/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2019.

## Built on by (most cited first, 18 of 18)

- [MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning](https://mlsanity.com/paper/2110.15352/) (2021)
- [Tracking Pedestrian Heads in Dense Crowd](https://mlsanity.com/paper/2103.13516/) (2021)
- [Tiny Machine Learning: Progress and Futures](https://mlsanity.com/paper/2403.19076/) (2024)
- [Going Deeper Into Face Detection: A Survey](https://mlsanity.com/paper/2103.14983/) (2021)
- [ASFD: Automatic and Scalable Face Detector](https://mlsanity.com/paper/2201.10781/) (2022)
- [EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection](https://mlsanity.com/paper/2204.01209/) (2022)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation](https://mlsanity.com/paper/2111.06500/) (2021)
- [MinUn: Accurate ML Inference on Microcontrollers](https://mlsanity.com/paper/2210.16556/) (2022)
- [EfficientFace: An Efficient Deep Network with Feature Enhancement for Accurate Face Detection](https://mlsanity.com/paper/2302.11816/) (2023)
- [YinYang-Net: Complementing Face and Body Information for Wild Gender Recognition](https://mlsanity.com/paper/2107.06847/) (2021)
- [Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion](https://mlsanity.com/paper/2311.16613/) (2023)
- [B-FPGM: Lightweight Face Detection via Bayesian-Optimized Soft FPGM Pruning](https://mlsanity.com/paper/2501.16917/) (2025)
- [EfficientSRFace: An Efficient Network with Super-Resolution Enhancement for Accurate Face Detection](https://mlsanity.com/paper/2306.02277/) (2023)
- [Inverted Non-maximum Suppression for more Accurate and Neater Face Detection](https://mlsanity.com/paper/2305.10593/) (2023)
- [A Comparative Study of Face Detection Algorithms for Masked Face Detection](https://mlsanity.com/paper/2305.11077/) (2023)
- [Skipped Feature Pyramid Network with Grid Anchor for Object Detection](https://mlsanity.com/paper/2310.14453/) (2023)
- [Transformer-Driven Multimodal Fusion for Explainable Suspiciousness Estimation in Visual Surveillance](https://mlsanity.com/paper/2512.09311/) (2025)

## Abstract (arXiv)

In this paper, we propose a new multi-scale face detector having an extremely tiny number of parameters (EXTD),less than 0.1 million, as well as achieving comparable performance to deep heavy detectors. While existing multi-scale face detectors extract feature maps with different scales from a single backbone network, our method generates the feature maps by iteratively reusing a shared lightweight and shallow backbone network. This iterative sharing of the backbone network significantly reduces the number of parameters, and also provides the abstract image semantics captured from the higher stage of the network layers to the lower-level feature map. The proposed idea is employed by various model architectures and evaluated by extensive experiments. From the experiments from WIDER FACE dataset, we show that the proposed face detector can handle faces with various scale and conditions, and achieved comparable performance to the more massive face detectors that few hundreds and tens times heavier in model size and floating point operations.