Papers › Face Alignment With Kernel Density Deep Neural Network
Face Alignment With Kernel Density Deep Neural Network
Lisha Chen, Hui Su, Qiang Ji
Deep neural networks achieve good performance in many computer vision problems such as face alignment. However, when the testing image is challenging due to low resolution, occlusion or adversarial attacks, the accuracy of a deep neural network suffers greatly. Therefore, it is important to quantify the uncertainty in its predictions. A probabilistic neural network with Gaussian distribution over the target is typically used to quantify uncertainty for regression problems. However, in real-world problems especially computer vision tasks, the Gaussian assumption is too strong. To model more general distributions, such as multi-modal or asymmetric distributions, we propose to develop a kernel density deep neural network. Specifically, for face alignment, we adapt state-of-the-art hourglass neural network into a probabilistic neural network framework with landmark probability map as its output. The model is trained by maximizing the conditional log likelihood. To exploit the output probability map, we extend the model to multi-stage so that the logits map from the previous stage can feed into the next stage to progressively improve the landmark detection accuracy. Extensive experiments on benchmark datasets against state-of-the-art unconstrained deep learning method demonstrate that the proposed kernel density network achieves comparable or superior performance in terms of prediction accuracy. It further provides aleatoric uncertainty estimation in predictions.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Face Alignment | 300W Split 2 | KDN | AUC@7 (box) | 67.3 | #4 of 7 | Archive leaderboard | report |
| Face Alignment | 300W Split 2 | KDN | NME (box) | 2.49 | #4 of 7 | Archive leaderboard | report |
| Face Alignment | 300W Split 2 (300W-LP) | KDN | AUC@7 (bbox) | 68.3 | #3 of 4 | Archive leaderboard | report |
| Face Alignment | 300W Split 2 (300W-LP) | KDN | NME (bbox) | 2.21 | #3 of 4 | Archive leaderboard | report |
| Face Alignment | AFLW-19 | KDN | AUC_box@0.07 (%, Full) | 60.3 | #23 of 23 | Archive leaderboard | report |
| Face Alignment | AFLW-19 | KDN | NME_box (%, Full) | 2.80 | #23 of 23 | Archive leaderboard | report |
| Face Alignment | COFW-68 (300WLP) | KDN | AUC@7 | 60.1 | #3 of 4 | Archive leaderboard | report |
| Face Alignment | COFW-68 (300WLP) | KDN | NME (box) | 2.73 | #3 of 4 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections