# Sample and Computation Redistribution for Efficient Face Detection

arXiv: https://arxiv.org/abs/2105.04714 · HTML: https://mlsanity.com/paper/2105.04714/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 51 references that are in the map.
- First posted on arXiv 10 May 2021.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [Bag of Tricks for Image Classification with Convolutional Neural Networks](https://mlsanity.com/paper/1812.01187/) (2018)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection](https://mlsanity.com/paper/1904.07392/) (2019)
- [Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network](https://mlsanity.com/paper/1803.07835/) (2018)
- [RetinaFace: Single-stage Dense Face Localisation in the Wild](https://mlsanity.com/paper/1905.00641/) (2019)
- [Revisiting ResNets: Improved Training and Scaling Strategies](https://mlsanity.com/paper/2103.07579/) (2021)
- [S3FD: Single Shot Scale-invariant Face Detector](https://mlsanity.com/paper/1708.05237/) (2017)
- [DSFD: Dual Shot Face Detector](https://mlsanity.com/paper/1810.10220/) (2018)
- [PyramidBox: A Context-assisted Single Shot Face Detector](https://mlsanity.com/paper/1803.07737/) (2018)
- [FaceBoxes: A CPU Real-time Face Detector with High Accuracy](https://mlsanity.com/paper/1708.05234/) (2017)
- [SSH: Single Stage Headless Face Detector](https://mlsanity.com/paper/1708.03979/) (2017)
- [OSTeC: One-Shot Texture Completion](https://mlsanity.com/paper/2012.15370/) (2020)

## Built on by (most cited first, 30 of 89)

- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)
- [A Survey of Multimodal Large Language Model from A Data-centric Perspective](https://mlsanity.com/paper/2405.16640/) (2024)
- [Expanding Accurate Person Recognition to New Altitudes and Ranges: The BRIAR Dataset](https://mlsanity.com/paper/2211.01917/) (2022)
- [Insert Anything: Image Insertion via In-Context Editing in DiT](https://mlsanity.com/paper/2504.15009/) (2025)
- [GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variations](https://mlsanity.com/paper/2305.19962/) (2023)
- [Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model](https://mlsanity.com/paper/2502.09533/) (2025)
- [YOLO5Face: Why Reinventing a Face Detector](https://mlsanity.com/paper/2105.12931/) (2021)
- [VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention](https://mlsanity.com/paper/2503.15138/) (2025)
- [Concat-ID: Towards Universal Identity-Preserving Video Synthesis](https://mlsanity.com/paper/2503.14151/) (2025)
- [There is a Time and Place for Reasoning Beyond the Image](https://mlsanity.com/paper/2203.00758/) (2022)
- [Towards Realistic Generative 3D Face Models](https://mlsanity.com/paper/2304.12483/) (2023)
- [InfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Shows](https://mlsanity.com/paper/2406.19875/) (2024)
- [ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation](https://mlsanity.com/paper/2510.11000/) (2025)
- [Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation](https://mlsanity.com/paper/2312.01220/) (2023)
- [ExpLLM: Towards Chain of Thought for Facial Expression Recognition](https://mlsanity.com/paper/2409.02828/) (2024)
- [ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow Generation](https://mlsanity.com/paper/2503.17671/) (2025)
- [Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics](https://mlsanity.com/paper/2402.09225/) (2024)
- [RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance](https://mlsanity.com/paper/2405.14677/) (2024)
- [3DMM-RF: Convolutional Radiance Fields for 3D Face Modeling](https://mlsanity.com/paper/2209.07366/) (2022)
- [OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking](https://mlsanity.com/paper/2504.02433/) (2025)
- [Playmate: Flexible Control of Portrait Animation via 3D-Implicit Space Guided Diffusion](https://mlsanity.com/paper/2502.07203/) (2025)
- [Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization](https://mlsanity.com/paper/2510.14255/) (2025)
- [UVMap-ID: A Controllable and Personalized UV Map Generative Model](https://mlsanity.com/paper/2404.14568/) (2024)
- [EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection](https://mlsanity.com/paper/2204.01209/) (2022)
- [VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention](https://mlsanity.com/paper/2412.02259/) (2024)
- [Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2504.15848/) (2025)
- [Monocular Identity-Conditioned Facial Reflectance Reconstruction](https://mlsanity.com/paper/2404.00301/) (2024)
- [Perspective Reconstruction of Human Faces by Joint Mesh and Landmark Regression](https://mlsanity.com/paper/2208.07142/) (2022)
- [Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Multi-View Performance Captures](https://mlsanity.com/paper/2510.14179/) (2025)
- [Towards Spatial Supersensing in the Wild](https://mlsanity.com/paper/2607.13681/) (2026)

## Abstract (arXiv)

Although tremendous strides have been made in uncontrolled face detection, efficient face detection with a low computation cost as well as high precision remains an open challenge. In this paper, we point out that training data sampling and computation distribution strategies are the keys to efficient and accurate face detection. Motivated by these observations, we introduce two simple but effective methods (1) Sample Redistribution (SR), which augments training samples for the most needed stages, based on the statistics of benchmark datasets; and (2) Computation Redistribution (CR), which reallocates the computation between the backbone, neck and head of the model, based on a meticulously defined search methodology. Extensive experiments conducted on WIDER FACE demonstrate the state-of-the-art efficiency-accuracy trade-off for the proposed scrfd family across a wide range of compute regimes. In particular, scrfdf34 outperforms the best competitor, TinaFace, by 3.86% (AP at hard set) while being more than 3× faster on GPUs with VGA-resolution images. We also release our code to facilitate future research.