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

• URL: http://arxiv.org/abs/2109.05721v1
• Date: Mon, 13 Sep 2021 06:05:28 GMT
• Title: ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment
• Authors: Yangyu Huang, Hao Yang, Chong Li, Jongyoo Kim, Fangyun Wei
• Abstract summary: 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. Inspired by this observation, we seek a way to leverage the error-bias property for better convergence of CNN model. We propose anisotropic direction loss (ADL) and anisotropic attention module (AAM) for coordinate and heatmap regression.
• Score: 28.301603455377435
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack [58.440711902319855]
  Edge perturbation is a method to modify graph structures. It can be categorized into two veins based on their effects on the performance of graph neural networks (GNNs) We propose a unified formulation and establish a clear boundary between two categories of edge perturbation methods.
  arXiv  Detail & Related papers  (2024-03-10T15:50:04Z)
• Parallel Vertex Diffusion for Unified Visual Grounding [38.94276071029081]
  Unified visual grounding pursues a simple and generic technical route to leverage multi-task data with less task-specific design. Most advanced methods typically present boxes and masks as a sequence to model referring detection and segmentation.
  arXiv  Detail & Related papers  (2023-03-13T15:51:38Z)
• Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding [51.48582649050054]
  We propose a representation normalization method which aims at disentangling the correlations between features of encoded sentences. We also propose Kernel-Whitening, a Nystrom kernel approximation method to achieve more thorough debiasing on nonlinear spurious correlations. Experiments show that Kernel-Whitening significantly improves the performance of BERT on out-of-distribution datasets while maintaining in-distribution accuracy.
  arXiv  Detail & Related papers  (2022-10-14T05:56:38Z)
• Feature Space Targeted Attacks by Statistic Alignment [74.40447383387574]
  Feature space targeted attacks perturb images by modulating their intermediate feature maps. The current choice of pixel-wise Euclidean Distance to measure the discrepancy is questionable because it unreasonably imposes a spatial-consistency constraint on the source and target features. We propose two novel approaches called Pair-wise Alignment Attack and Global-wise Alignment Attack, which attempt to measure similarities between feature maps by high-order statistics.
  arXiv  Detail & Related papers  (2021-05-25T03:46:39Z)
• Directional Graph Networks [17.11861614285746]
  We propose the first globally consistent anisotropic kernels for graph neural networks (GNNs) By defining a vector field in the graph, we develop a method of applying directional derivatives and smoothing by projecting node-specific messages into the field. We show that the method generalizes CNNs on an $n$-dimensional grid and is provably more discriminative than standard GNNs.
  arXiv  Detail & Related papers  (2020-10-06T16:31:27Z)
• PropagationNet: Propagate Points to Curve to Learn Structure Information [79.65125870257009]
  We present a novel structure-infused face alignment algorithm based on heatmap regression. We also propose a Focal Wing Loss for mining and emphasizing the difficult samples under in-the-wild condition. Our method achieves 4.05% mean error on WFLW, 2.93% mean error on 300W full-set, and 3.71% mean error on COFW.
  arXiv  Detail & Related papers  (2020-06-25T11:08:59Z)
• Unsupervised Performance Analysis of 3D Face Alignment with a Statistically Robust Confidence Test [32.43769049247355]
  This paper addresses the problem of analysing the performance of 3D face alignment (3DFA) The core ingredient of the proposed methodology is the robust estimation of the rigid transformation between predicted landmarks and model landmarks. The results show that the proposed analysis is consistent with supervised metrics and that it can be used to measure the accuracy of both predicted landmarks and of automatically annotated 3DFA datasets.
  arXiv  Detail & Related papers  (2020-04-14T14:33:57Z)
• High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification [84.43394420267794]
  We propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. Our framework significantly outperforms state-of-the-art by6.5%mAP scores on Occluded-Duke dataset.
  arXiv  Detail & Related papers  (2020-03-18T12:18:35Z)
• On the Arbitrary-Oriented Object Detection: Classification based Approaches Revisited [94.5455251250471]
  We first show that the boundary problem suffered in existing dominant regression-based rotation detectors, is caused by angular periodicity or corner ordering. We transform the angular prediction task from a regression problem to a classification one. For the resulting circularly distributed angle classification problem, we first devise a Circular Smooth Label technique to handle the periodicity of angle and increase the error tolerance to adjacent angles.
  arXiv  Detail & Related papers  (2020-03-12T03:23:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.