# Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources

arXiv: https://arxiv.org/abs/1703.00862 · HTML: https://mlsanity.com/paper/1703.00862/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2017.

## Built on by (most cited first, 23 of 23)

- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [A comprehensive review of Binary Neural Network](https://mlsanity.com/paper/2110.06804/) (2021)
- [ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment](https://mlsanity.com/paper/2109.05721/) (2021)
- [DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image](https://mlsanity.com/paper/2204.03688/) (2022)
- [Multi-task head pose estimation in-the-wild](https://mlsanity.com/paper/2202.02299/) (2022)
- [Fast Facial Landmark Detection and Applications: A Survey](https://mlsanity.com/paper/2101.10808/) (2021)
- [Subpixel Heatmap Regression for Facial Landmark Localization](https://mlsanity.com/paper/2111.02360/) (2021)
- [INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold](https://mlsanity.com/paper/2204.07439/) (2022)
- [Generalizable Face Landmarking Guided by Conditional Face Warping](https://mlsanity.com/paper/2404.12322/) (2024)
- [Bias-Variance Tradeoffs in Single-Sample Binary Gradient Estimators](https://mlsanity.com/paper/2110.03549/) (2021)
- [From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery](https://mlsanity.com/paper/2205.15895/) (2022)
- [Taming Binarized Neural Networks and Mixed-Integer Programs](https://mlsanity.com/paper/2310.04469/) (2023)
- [Human Modelling and Pose Estimation Overview](https://mlsanity.com/paper/2406.19290/) (2024)
- [An Efficient Multitask Neural Network for Face Alignment, Head Pose Estimation and Face Tracking](https://mlsanity.com/paper/2103.07615/) (2021)
- [3D Dense Face Alignment with Fused Features by Aggregating CNNs and GCNs](https://mlsanity.com/paper/2203.04643/) (2022)
- [Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimation](https://mlsanity.com/paper/2104.10414/) (2021)
- [Defensive Tensorization](https://mlsanity.com/paper/2110.13859/) (2021)
- [OVeNet: Offset Vector Network for Semantic Segmentation](https://mlsanity.com/paper/2303.14516/) (2023)
- [DogFLW: Dog Facial Landmarks in the Wild Dataset](https://mlsanity.com/paper/2405.11501/) (2024)
- [FineNet: Frame Interpolation and Enhancement for Face Video Deblurring](https://mlsanity.com/paper/2103.00871/) (2021)
- [Towards a Unified View of Affinity-Based Knowledge Distillation](https://mlsanity.com/paper/2209.15555/) (2022)
- [3D Face Alignment Through Fusion of Head Pose Information and Features](https://mlsanity.com/paper/2308.13327/) (2023)
- [NeoLoc-68: End-to-end 68-point neonatal facial landmark localisation in neonatal clinical environments](https://mlsanity.com/paper/2606.20823/) (2026)

## Abstract (arXiv)

Our goal is to design architectures that retain the groundbreaking performance of CNNs for landmark localization and at the same time are lightweight, compact and suitable for applications with limited computational resources. To this end, we make the following contributions: (a) we are the first to study the effect of neural network binarization on localization tasks, namely human pose estimation and face alignment. We exhaustively evaluate various design choices, identify performance bottlenecks, and more importantly propose multiple orthogonal ways to boost performance. (b) Based on our analysis, we propose a novel hierarchical, parallel and multi-scale residual architecture that yields large performance improvement over the standard bottleneck block while having the same number of parameters, thus bridging the gap between the original network and its binarized counterpart. (c) We perform a large number of ablation studies that shed light on the properties and the performance of the proposed block. (d) We present results for experiments on the most challenging datasets for human pose estimation and face alignment, reporting in many cases state-of-the-art performance. Code can be downloaded from https://www.adrianbulat.com/binary-cnn-landmarks