# From Facial Parts Responses to Face Detection: A Deep Learning Approach

arXiv: https://arxiv.org/abs/1509.06451 · HTML: https://mlsanity.com/paper/1509.06451/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2015.

## Built on by (most cited first, 30 of 42)

- [Linear Adversarial Concept Erasure](https://mlsanity.com/paper/2201.12091/) (2022)
- [PnP-Flow: Plug-and-Play Image Restoration with Flow Matching](https://mlsanity.com/paper/2410.02423/) (2024)
- [Poisson Flow Generative Models](https://mlsanity.com/paper/2209.11178/) (2022)
- [Stable Target Field for Reduced Variance Score Estimation in Diffusion Models](https://mlsanity.com/paper/2302.00670/) (2023)
- [Generalizable Implicit Neural Representations via Instance Pattern Composers](https://mlsanity.com/paper/2211.13223/) (2022)
- [MIDV-2020: A Comprehensive Benchmark Dataset for Identity Document Analysis](https://mlsanity.com/paper/2107.00396/) (2021)
- [Benchmarking Adversarially Robust Quantum Machine Learning at Scale](https://mlsanity.com/paper/2211.12681/) (2022)
- [Flower: A Flow-Matching Solver for Inverse Problems](https://mlsanity.com/paper/2509.26287/) (2025)
- [Context Understanding in Computer Vision: A Survey](https://mlsanity.com/paper/2302.05011/) (2023)
- [Dodging Attack Using Carefully Crafted Natural Makeup](https://mlsanity.com/paper/2109.06467/) (2021)
- [CNS-Net: Conservative Novelty Synthesizing Network for Malware Recognition in an Open-set Scenario](https://mlsanity.com/paper/2305.01236/) (2023)
- [Subpixel Heatmap Regression for Facial Landmark Localization](https://mlsanity.com/paper/2111.02360/) (2021)
- [Fed-FSNet: Mitigating Non-I.I.D. Federated Learning via Fuzzy Synthesizing Network](https://mlsanity.com/paper/2208.12044/) (2022)
- [Sampling from Bayesian Neural Network Posteriors with Symmetric Minibatch Splitting Langevin Dynamics](https://mlsanity.com/paper/2410.19780/) (2024)
- [Towards Fairer and More Efficient Federated Learning via Multidimensional Personalized Edge Models](https://mlsanity.com/paper/2302.04464/) (2023)
- [MDENet: Multi-modal Dual-embedding Networks for Malware Open-set Recognition](https://mlsanity.com/paper/2305.01245/) (2023)
- [SFP: Spurious Feature-targeted Pruning for Out-of-Distribution Generalization](https://mlsanity.com/paper/2305.11615/) (2023)
- [The Generation Phases of Flow Matching: a Denoising Perspective](https://mlsanity.com/paper/2510.24830/) (2025)
- [Stochastic Adaptive Activation Function](https://mlsanity.com/paper/2210.11672/) (2022)
- [Training Flow Matching: The Role of Weighting and Parameterization](https://mlsanity.com/paper/2603.06454/) (2026)
- [LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds](https://mlsanity.com/paper/2110.04727/) (2021)
- [Plug-and-Play Image Restoration with Flow Matching: A Continuous Viewpoint](https://mlsanity.com/paper/2512.04283/) (2025)
- [Unsupervised Single-shot Depth Estimation using Perceptual Reconstruction](https://mlsanity.com/paper/2201.12170/) (2022)
- [PINCH: An Adversarial Extraction Attack Framework for Deep Learning Models](https://mlsanity.com/paper/2209.06300/) (2022)
- [Radio Signal Classification by Adversarially Robust Quantum Machine Learning](https://mlsanity.com/paper/2312.07821/) (2023)
- [Anti-Aesthetics: Protecting Facial Privacy against Customized Text-to-Image Synthesis](https://mlsanity.com/paper/2504.12129/) (2025)
- [Trajectory Stitching for Solving Inverse Problems with Flow-Based Models](https://mlsanity.com/paper/2602.08538/) (2026)
- [Achieving Explainability for Plant Disease Classification with Disentangled Variational Autoencoders](https://mlsanity.com/paper/2102.03082/) (2021)
- [Describing Sets of Images with Textual-PCA](https://mlsanity.com/paper/2210.12112/) (2022)
- [Real-time AdaBoost cascade face tracker based on likelihood map and optical flow](https://mlsanity.com/paper/2210.13885/) (2022)

## Abstract (arXiv)

In this paper, we propose a novel deep convolutional network (DCN) that achieves outstanding performance on FDDB, PASCAL Face, and AFW. Specifically, our method achieves a high recall rate of 90.99% on the challenging FDDB benchmark, outperforming the state-of-the-art method by a large margin of 2.91%. Importantly, we consider finding faces from a new perspective through scoring facial parts responses by their spatial structure and arrangement. The scoring mechanism is carefully formulated considering challenging cases where faces are only partially visible. This consideration allows our network to detect faces under severe occlusion and unconstrained pose variation, which are the main difficulty and bottleneck of most existing face detection approaches. We show that despite the use of DCN, our network can achieve practical runtime speed.