PropagationNet: Propagate Points to Curve to Learn Structure Information

• URL: http://arxiv.org/abs/2006.14308v1
• Date: Thu, 25 Jun 2020 11:08:59 GMT
• Title: PropagationNet: Propagate Points to Curve to Learn Structure Information
• Authors: Xiehe Huang, Weihong Deng, Haifeng Shen, Xiubao Zhang, Jieping Ye
• Abstract summary: 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.
• Score: 79.65125870257009
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning technique has dramatically boosted the performance of face alignment algorithms. However, due to large variability and lack of samples, the alignment problem in unconstrained situations, \emph{e.g}\onedot large head poses, exaggerated expression, and uneven illumination, is still largely unsolved. In this paper, we explore the instincts and reasons behind our two proposals, \emph{i.e}\onedot Propagation Module and Focal Wing Loss, to tackle the problem. Concretely, we present a novel structure-infused face alignment algorithm based on heatmap regression via propagating landmark heatmaps to boundary heatmaps, which provide structure information for further attention map generation. Moreover, we propose a Focal Wing Loss for mining and emphasizing the difficult samples under in-the-wild condition. In addition, we adopt methods like CoordConv and Anti-aliased CNN from other fields that address the shift-variance problem of CNN for face alignment. When implementing extensive experiments on different benchmarks, \emph{i.e}\onedot WFLW, 300W, and COFW, our method outperforms state-of-the-arts by a significant margin. Our proposed approach achieves 4.05\% mean error on WFLW, 2.93\% mean error on 300W full-set, and 3.71\% mean error on COFW.

Related papers

• On the representation and methodology for wide and short range head pose estimation [48.87319013701136]
  Head pose estimation (HPE) is a problem of interest in computer vision. Recent applications require the analysis of faces in the full 360deg rotation range. Traditional approaches to solve the semi-frontal and profile cases are not directly amenable for the full rotation case.
  arXiv  Detail & Related papers  (2024-01-11T10:20:37Z)
• LoLep: Single-View View Synthesis with Locally-Learned Planes and Self-Attention Occlusion Inference [66.45326873274908]
  We propose a novel method, LoLep, which regresses Locally-Learned planes from a single RGB image to represent scenes accurately. Compared to MINE, our approach has an LPIPS reduction of 4.8%-9.0% and an RV reduction of 73.9%-83.5%.
  arXiv  Detail & Related papers  (2023-07-23T03:38:55Z)
• Subpixel Heatmap Regression for Facial Landmark Localization [65.41270740933656]
  Heatmap regression approaches suffer from discretization-induced errors related to both the heatmap encoding and decoding process. We propose a new approach for the heatmap encoding and decoding process by leveraging the underlying continuous distribution. Our approach offers noticeable gains across multiple datasets setting a new state-of-the-art result in facial landmark localization.
  arXiv  Detail & Related papers  (2021-11-03T17:21:28Z)
• ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment [28.301603455377435]
  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.
  arXiv  Detail & Related papers  (2021-09-13T06:05:28Z)
• Physics-Informed Graph Learning for Robust Fault Location in Distribution Systems [2.984934409689467]
  Rapid growth of distributed energy resources potentially increases power grid instability. One promising strategy is to employ data in power grids to efficiently respond to abnormal events (e.g., faults) by detection and location. We propose a physics-informed graph learning framework of two stages to handle these challenges when locating faults.
  arXiv  Detail & Related papers  (2021-07-05T21:18:37Z)
• Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm [93.80082636284922]
  Sparse adversarial attacks can fool deep networks (DNNs) by only perturbing a few pixels. Recent efforts combine it with another l_infty perturbation on magnitudes. We propose a homotopy algorithm to tackle the sparsity and neural perturbation framework.
  arXiv  Detail & Related papers  (2021-06-10T20:11:36Z)
• SDAN: Squared Deformable Alignment Network for Learning Misaligned Optical Zoom [5.202871995038932]
  Deep Neural Network (DNN) based super-resolution algorithms have greatly improved the quality of the generated images. These algorithms often yield significant artifacts when dealing with real-world super-resolution problems. We introduce a Squared Deformable Alignment Network (SDAN) to address this issue.
  arXiv  Detail & Related papers  (2021-04-02T01:58:00Z)
• Where, What, Whether: Multi-modal Learning Meets Pedestrian Detection [23.92066492219922]
  We decompose the pedestrian detection task into textbftextitWhere, textbftextitWhat and textbftextitWhether. We achieve state-of-the-art results on widely used datasets (Citypersons and Caltech)
  arXiv  Detail & Related papers  (2020-12-20T10:15:39Z)
• ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection [147.10751375922035]
  We propose the ContourNet, which effectively handles false positives and large scale variance of scene texts. Our method effectively suppresses these false positives by only outputting predictions with high response value in both directions.
  arXiv  Detail & Related papers  (2020-04-10T08:15:23Z)

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.