# ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment

arXiv: https://arxiv.org/abs/2109.05721 · HTML: https://mlsanity.com/paper/2109.05721/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 57 references that are in the map.
- First posted on arXiv 13 Sep 2021.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [Convolutional Pose Machines](https://mlsanity.com/paper/1602.00134/) (2016)
- [An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution](https://mlsanity.com/paper/1807.03247/) (2018)
- [DeepPose: Human Pose Estimation via Deep Neural Networks](https://mlsanity.com/paper/1312.4659/) (2013)
- [Deep Face Recognition: A Survey](https://mlsanity.com/paper/1804.06655/) (2018)
- [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)
- [Towards Open-Set Identity Preserving Face Synthesis](https://mlsanity.com/paper/1803.11182/) (2018)
- [Mask-Guided Portrait Editing with Conditional GANs](https://mlsanity.com/paper/1905.10346/) (2019)
- [Style Aggregated Network for Facial Landmark Detection](https://mlsanity.com/paper/1803.04108/) (2018)
- [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)
- [Learning Deep Representation for Face Alignment with Auxiliary Attributes](https://mlsanity.com/paper/1408.3967/) (2014)
- [Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources](https://mlsanity.com/paper/1703.00862/) (2017)
- [Dynamic Attention-controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-set Sample Weighting](https://mlsanity.com/paper/1611.05396/) (2016)
- [Quantized Densely Connected U-Nets for Efficient Landmark Localization](https://mlsanity.com/paper/1808.02194/) (2018)
- [Disentangling 3D Pose in A Dendritic CNN for Unconstrained 2D Face Alignment](https://mlsanity.com/paper/1802.06713/) (2018)
- [Robust Facial Landmark Detection under Significant Head Poses and Occlusion](https://mlsanity.com/paper/1709.08127/) (2017)
- [Joint Multi-view Face Alignment in the Wild](https://mlsanity.com/paper/1708.06023/) (2017)
- [PropagationNet: Propagate Points to Curve to Learn Structure Information](https://mlsanity.com/paper/2006.14308/) (2020)
- [ACE-Net: Fine-Level Face Alignment through Anchors and Contours Estimation](https://mlsanity.com/paper/2012.01461/) (2020)

## Built on by (most cited first, 30 of 34)

- [General Facial Representation Learning in a Visual-Linguistic Manner](https://mlsanity.com/paper/2112.03109/) (2021)
- [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)
- [Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models](https://mlsanity.com/paper/2304.00600/) (2023)
- [StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation](https://mlsanity.com/paper/2305.19012/) (2023)
- [Shape Preserving Facial Landmarks with Graph Attention Networks](https://mlsanity.com/paper/2210.07233/) (2022)
- [Self-Supervised Facial Representation Learning with Facial Region Awareness](https://mlsanity.com/paper/2403.02138/) (2024)
- [Precise Facial Landmark Detection by Reference Heatmap Transformer](https://mlsanity.com/paper/2303.07840/) (2023)
- [Faceptor: A Generalist Model for Face Perception](https://mlsanity.com/paper/2403.09500/) (2024)
- [T-FAKE: Synthesizing Thermal Images for Facial Landmarking](https://mlsanity.com/paper/2408.15127/) (2024)
- [SCE-MAE: Selective Correspondence Enhancement with Masked Autoencoder for Self-Supervised Landmark Estimation](https://mlsanity.com/paper/2405.18322/) (2024)
- [Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection](https://mlsanity.com/paper/2411.07167/) (2024)
- [Proto-Former: Unified Facial Landmark Detection by Prototype Transformer](https://mlsanity.com/paper/2510.15338/) (2025)
- [FreeEnricher: Enriching Face Landmarks without Additional Cost](https://mlsanity.com/paper/2212.09525/) (2022)
- [Automated Detection of Cat Facial Landmarks](https://mlsanity.com/paper/2310.09793/) (2023)
- [ProS: Facial Omni-Representation Learning via Prototype-based Self-Distillation](https://mlsanity.com/paper/2311.01929/) (2023)
- [Multi-Domain Multi-Definition Landmark Localization for Small Datasets](https://mlsanity.com/paper/2203.10358/) (2022)
- [Fiducial Focus Augmentation for Facial Landmark Detection](https://mlsanity.com/paper/2402.15044/) (2024)
- [ORFormer: Occlusion-Robust Transformer for Accurate Facial Landmark Detection](https://mlsanity.com/paper/2412.13174/) (2024)
- [FGTBT: Frequency-Guided Task-Balancing Transformer for Unified Facial Landmark Detection](https://mlsanity.com/paper/2601.12863/) (2026)
- [LPMM: Intuitive Pose Control for Neural Talking-Head Model via Landmark-Parameter Morphable Model](https://mlsanity.com/paper/2305.10456/) (2023)
- [Towards Multi-domain Face Landmark Detection with Synthetic Data from Diffusion model](https://mlsanity.com/paper/2401.13191/) (2024)
- [Improving Facial Landmark Detection Accuracy and Efficiency with Knowledge Distillation](https://mlsanity.com/paper/2404.06029/) (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)
- [Event-based Facial Keypoint Alignment via Cross-Modal Fusion Attention and Self-Supervised Multi-Event Representation Learning](https://mlsanity.com/paper/2509.24968/) (2025)
- [Supervision-by-Hallucination-and-Transfer: A Weakly-Supervised Approach for Robust and Precise Facial Landmark Detection](https://mlsanity.com/paper/2601.12919/) (2026)
- [OccFace: Unified Occlusion-Aware Facial Landmark Detection with Per-Point Visibility](https://mlsanity.com/paper/2602.10728/) (2026)
- [FreqFLD: Towards All-in-One Facial Landmark Detection via Frequency Modulation](https://mlsanity.com/paper/2609.10278/) (2026)

## Abstract (arXiv)

The recent progress of CNN has dramatically improved face alignment performance. However, few works have paid attention to the error-bias with respect to error distribution of facial landmarks. In this paper, we investigate the error-bias issue in face alignment, where the distributions of landmark errors tend to spread along the tangent line to landmark curves. This error-bias is not trivial since it is closely connected to the ambiguous landmark labeling task. Inspired by this observation, we seek a way to leverage the error-bias property for better convergence of CNN model. To this end, we propose anisotropic direction loss (ADL) and anisotropic attention module (AAM) for coordinate and heatmap regression, respectively. ADL imposes strong binding force in normal direction for each landmark point on facial boundaries. On the other hand, AAM is an attention module which can get anisotropic attention mask focusing on the region of point and its local edge connected by adjacent points, it has a stronger response in tangent than in normal, which means relaxed constraints in the tangent. These two methods work in a complementary manner to learn both facial structures and texture details. Finally, we integrate them into an optimized end-to-end training pipeline named ADNet. Our ADNet achieves state-of-the-art results on 300W, WFLW and COFW datasets, which demonstrates the effectiveness and robustness.