# Semantic Alignment: Finding Semantically Consistent Ground-truth for Facial Landmark Detection

arXiv: https://arxiv.org/abs/1903.10661 · HTML: https://mlsanity.com/paper/1903.10661/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Mar 2019.

## Built on by (most cited first, 16 of 16)

- [STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection](https://mlsanity.com/paper/2306.02763/) (2023)
- [Towards Accurate Facial Landmark Detection via Cascaded Transformers](https://mlsanity.com/paper/2208.10808/) (2022)
- [Precise Facial Landmark Detection by Reference Heatmap Transformer](https://mlsanity.com/paper/2303.07840/) (2023)
- [Semi-supervised Anatomical Landmark Detection via Shape-regulated Self-training](https://mlsanity.com/paper/2105.13593/) (2021)
- [U-LanD: Uncertainty-Driven Video Landmark Detection](https://mlsanity.com/paper/2102.01586/) (2021)
- [Modeling Annotation Uncertainty with Gaussian Heatmaps in Landmark Localization](https://mlsanity.com/paper/2109.09533/) (2021)
- [Robust and Precise Facial Landmark Detection by Self-Calibrated Pose Attention Network](https://mlsanity.com/paper/2112.12328/) (2021)
- [When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model](https://mlsanity.com/paper/2105.13150/) (2021)
- [Rethinking Self-training for Semi-supervised Landmark Detection: A Selection-free Approach](https://mlsanity.com/paper/2404.04556/) (2024)
- [Reasoning Structural Relation for Occlusion-Robust Facial Landmark Localization](https://mlsanity.com/paper/2112.10087/) (2021)
- [Separable Batch Normalization for Robust Facial Landmark Localization with Cross-protocol Network Training](https://mlsanity.com/paper/2101.06663/) (2021)
- [Knowing When to Quit: Selective Cascaded Regression with Patch Attention for Real-Time Face Alignment](https://mlsanity.com/paper/2108.00377/) (2021)
- [Heatmap Regression without Soft-Argmax for Facial Landmark Detection](https://mlsanity.com/paper/2508.14929/) (2025)
- [Supervision-by-Hallucination-and-Transfer: A Weakly-Supervised Approach for Robust and Precise Facial Landmark Detection](https://mlsanity.com/paper/2601.12919/) (2026)
- [LocalEyenet: Deep Attention framework for Localization of Eyes](https://mlsanity.com/paper/2303.12728/) (2023)
- [Markerless Head Tracking for Accurate and Accessible Neuronavigation](https://mlsanity.com/paper/2602.07052/) (2026)

## Abstract (arXiv)

Recently, deep learning based facial landmark detection has achieved great success. Despite this, we notice that the semantic ambiguity greatly degrades the detection performance. Specifically, the semantic ambiguity means that some landmarks (e.g. those evenly distributed along the face contour) do not have clear and accurate definition, causing inconsistent annotations by annotators. Accordingly, these inconsistent annotations, which are usually provided by public databases, commonly work as the ground-truth to supervise network training, leading to the degraded accuracy. To our knowledge, little research has investigated this problem. In this paper, we propose a novel probabilistic model which introduces a latent variable, i.e. the 'real' ground-truth which is semantically consistent, to optimize. This framework couples two parts (1) training landmark detection CNN and (2) searching the 'real' ground-truth. These two parts are alternatively optimized: the searched 'real' ground-truth supervises the CNN training; and the trained CNN assists the searching of 'real' ground-truth. In addition, to recover the unconfidently predicted landmarks due to occlusion and low quality, we propose a global heatmap correction unit (GHCU) to correct outliers by considering the global face shape as a constraint. Extensive experiments on both image-based (300W and AFLW) and video-based (300-VW) databases demonstrate that our method effectively improves the landmark detection accuracy and achieves the state of the art performance.