# When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model

arXiv: https://arxiv.org/abs/2105.13150 · HTML: https://mlsanity.com/paper/2105.13150/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 41 references that are in the map.
- First posted on arXiv 27 May 2021.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Face2Face: Real-time Face Capture and Reenactment of RGB Videos](https://mlsanity.com/paper/2007.14808/) (2020)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [Look at Boundary: A Boundary-Aware Face Alignment Algorithm](https://mlsanity.com/paper/1805.10483/) (2018)
- [Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression](https://mlsanity.com/paper/1904.07399/) (2019)
- [Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks](https://mlsanity.com/paper/1711.06753/) (2017)
- [LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood](https://mlsanity.com/paper/2004.02980/) (2020)
- [Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild](https://mlsanity.com/paper/2003.03771/) (2020)
- [Style Aggregated Network for Facial Landmark Detection](https://mlsanity.com/paper/1803.04108/) (2018)
- [Structured Landmark Detection via Topology-Adapting Deep Graph Learning](https://mlsanity.com/paper/2004.08190/) (2020)
- [DeCaFA: Deep Convolutional Cascade for Face Alignment In The Wild](https://mlsanity.com/paper/1904.02549/) (2019)
- [Improving Landmark Localization with Semi-Supervised Learning](https://mlsanity.com/paper/1709.01591/) (2017)
- [Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Translation](https://mlsanity.com/paper/1908.06440/) (2019)
- [Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection](https://mlsanity.com/paper/1908.02116/) (2019)
- [Quantized Densely Connected U-Nets for Efficient Landmark Localization](https://mlsanity.com/paper/1808.02194/) (2018)
- [Semantic Alignment: Finding Semantically Consistent Ground-truth for Facial Landmark Detection](https://mlsanity.com/paper/1903.10661/) (2019)
- [Laplace Landmark Localization](https://mlsanity.com/paper/1903.11633/) (2019)

## Built on by (most cited first, 3 of 3)

- [Towards Accurate Facial Landmark Detection via Cascaded Transformers](https://mlsanity.com/paper/2208.10808/) (2022)
- [Unsupervised Domain Adaptation for Anatomical Landmark Detection](https://mlsanity.com/paper/2308.13286/) (2023)
- [Rethinking Self-training for Semi-supervised Landmark Detection: A Selection-free Approach](https://mlsanity.com/paper/2404.04556/) (2024)

## Abstract (arXiv)

In recent years, significant progress has been made in the research of facial landmark detection. However, few prior works have thoroughly discussed about models for practical applications. Instead, they often focus on improving a couple of issues at a time while ignoring the others. To bridge this gap, we aim to explore a practical model that is accurate, robust, efficient, generalizable, and end-to-end trainable at the same time. To this end, we first propose a baseline model equipped with one transformer decoder as detection head. In order to achieve a better accuracy, we further propose two lightweight modules, namely dynamic query initialization (DQInit) and query-aware memory (QAMem). Specifically, DQInit dynamically initializes the queries of decoder from the inputs, enabling the model to achieve as good accuracy as the ones with multiple decoder layers. QAMem is designed to enhance the discriminative ability of queries on low-resolution feature maps by assigning separate memory values to each query rather than a shared one. With the help of QAMem, our model removes the dependence on high-resolution feature maps and is still able to obtain superior accuracy. Extensive experiments and analysis on three popular benchmarks show the effectiveness and practical advantages of the proposed model. Notably, our model achieves new state of the art on WFLW as well as competitive results on 300W and COFW, while still running at 50+ FPS.