# Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Translation

arXiv: https://arxiv.org/abs/1908.06440 · HTML: https://mlsanity.com/paper/1908.06440/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Aug 2019.

## Built on by (most cited first, 30 of 33)

- [Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning](https://mlsanity.com/paper/2203.06541/) (2022)
- [STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection](https://mlsanity.com/paper/2306.02763/) (2023)
- [Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields](https://mlsanity.com/paper/2206.08361/) (2022)
- [Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models](https://mlsanity.com/paper/2304.00600/) (2023)
- [Shape Preserving Facial Landmarks with Graph Attention Networks](https://mlsanity.com/paper/2210.07233/) (2022)
- [Subpixel Heatmap Regression for Facial Landmark Localization](https://mlsanity.com/paper/2111.02360/) (2021)
- [Faceptor: A Generalist Model for Face Perception](https://mlsanity.com/paper/2403.09500/) (2024)
- [What Makes for Good Tokenizers in Vision Transformer?](https://mlsanity.com/paper/2212.11115/) (2022)
- [One-Shot Medical Landmark Localization by Edge-Guided Transform and Noisy Landmark Refinement](https://mlsanity.com/paper/2208.00453/) (2022)
- [FaceShield: Defending Facial Image against Deepfake Threats](https://mlsanity.com/paper/2412.09921/) (2024)
- [Robust and Precise Facial Landmark Detection by Self-Calibrated Pose Attention Network](https://mlsanity.com/paper/2112.12328/) (2021)
- [Generalizable Face Landmarking Guided by Conditional Face Warping](https://mlsanity.com/paper/2404.12322/) (2024)
- [Landmark Breaker: Obstructing DeepFake By Disturbing Landmark Extraction](https://mlsanity.com/paper/2102.00798/) (2021)
- [Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection](https://mlsanity.com/paper/2411.07167/) (2024)
- [Landmarks Augmentation with Manifold-Barycentric Oversampling](https://mlsanity.com/paper/2104.00925/) (2021)
- [When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model](https://mlsanity.com/paper/2105.13150/) (2021)
- [FreeEnricher: Enriching Face Landmarks without Additional Cost](https://mlsanity.com/paper/2212.09525/) (2022)
- [KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration](https://mlsanity.com/paper/2305.16437/) (2023)
- [ProS: Facial Omni-Representation Learning via Prototype-based Self-Distillation](https://mlsanity.com/paper/2311.01929/) (2023)
- [Rethinking Self-training for Semi-supervised Landmark Detection: A Selection-free Approach](https://mlsanity.com/paper/2404.04556/) (2024)
- [An Efficient Multitask Neural Network for Face Alignment, Head Pose Estimation and Face Tracking](https://mlsanity.com/paper/2103.07615/) (2021)
- [Multi-Domain Multi-Definition Landmark Localization for Small Datasets](https://mlsanity.com/paper/2203.10358/) (2022)
- [POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position Search](https://mlsanity.com/paper/2410.09583/) (2024)
- [Mitigating Knowledge Discrepancies among Multiple Datasets for Task-agnostic Unified Face Alignment](https://mlsanity.com/paper/2503.22359/) (2025)
- [PaCo-FR: Patch-Pixel Aligned End-to-End Codebook Learning for Facial Representation Pre-training](https://mlsanity.com/paper/2508.09691/) (2025)
- [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)
- [LDDMM-Face: Large Deformation Diffeomorphic Metric Learning for Flexible and Consistent Face Alignment](https://mlsanity.com/paper/2108.00690/) (2021)
- [CGOF++: Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields](https://mlsanity.com/paper/2211.13251/) (2022)
- [Semantic Style Transfer for Enhancing Animal Facial Landmark Detection](https://mlsanity.com/paper/2505.05640/) (2025)

## Abstract (arXiv)

Facial landmark detection, or face alignment, is a fundamental task that has been extensively studied. In this paper, we investigate a new perspective of facial landmark detection and demonstrate it leads to further notable improvement. Given that any face images can be factored into space of style that captures lighting, texture and image environment, and a style-invariant structure space, our key idea is to leverage disentangled style and shape space of each individual to augment existing structures via style translation. With these augmented synthetic samples, our semi-supervised model surprisingly outperforms the fully-supervised one by a large margin. Extensive experiments verify the effectiveness of our idea with state-of-the-art results on WFLW, 300W, COFW, and AFLW datasets. Our proposed structure is general and could be assembled into any face alignment frameworks. The code is made publicly available at https://github.com/thesouthfrog/stylealign.