Heatmap Regression via Randomized Rounding

by   Baosheng Yu, et al.

Heatmap regression has become the mainstream methodology for deep learning-based semantic landmark localization, including in facial landmark localization and human pose estimation. Though heatmap regression is robust to large variations in pose, illumination, and occlusion in unconstrained settings, it usually suffers from a sub-pixel localization problem. Specifically, considering that the activation point indices in heatmaps are always integers, quantization error thus appears when using heatmaps as the representation of numerical coordinates. Previous methods to overcome the sub-pixel localization problem usually rely on high-resolution heatmaps. As a result, there is always a trade-off between achieving localization accuracy and computational cost, where the computational complexity of heatmap regression depends on the heatmap resolution in a quadratic manner. In this paper, we formally analyze the quantization error of vanilla heatmap regression and propose a simple yet effective quantization system to address the sub-pixel localization problem. The proposed quantization system induced by the randomized rounding operation 1) encodes the fractional part of numerical coordinates into the ground truth heatmap using a probabilistic approach during training; and 2) decodes the predicted numerical coordinates from a set of activation points during testing. We prove that the proposed quantization system for heatmap regression is unbiased and lossless. Experimental results on four popular facial landmark localization datasets (WFLW, 300W, COFW, and AFLW) demonstrate the effectiveness of the proposed method for efficient and accurate semantic landmark localization. Code is available at http://github.com/baoshengyu/H3R.



There are no comments yet.


page 4

page 11

page 12

page 14


Attentive One-Dimensional Heatmap Regression for Facial Landmark Detection and Tracking

Although heatmap regression is considered a state-of-the-art method to l...

Adaloss: Adaptive Loss Function for Landmark Localization

Landmark localization is a challenging problem in computer vision with a...

Subpixel Heatmap Regression for Facial Landmark Localization

Deep Learning models based on heatmap regression have revolutionized the...

Towards Highly Accurate and Stable Face Alignment for High-Resolution Videos

In recent years, heatmap regression based models have shown their effect...

Quantized Densely Connected U-Nets for Efficient Landmark Localization

In this paper, we propose quantized densely connected U-Nets for efficie...

Facial Landmark Point Localization using Coarse-to-Fine Deep Recurrent Neural Network

Facial landmark point localization is a typical problem in computer visi...

PFLD: A Practical Facial Landmark Detector

Being accurate, efficient, and compact is essential to a facial landmark...

Code Repositories


Heatmap Regression via Randomized Rounding

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.