By the same authors

Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Author(s)

  • Zhenhua Feng
  • Josef Kittler
  • Muhammad Awais
  • Patrik Huber
  • Xiao-Jun Wu

Department/unit(s)

Publication details

Title of host publicationProceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
DatePublished - 14 Dec 2018
Pages2235-2245
Number of pages11
PublisherIEEE Computer Society
Original languageEnglish
ISBN (Electronic)978-1-5386-6420-9

Abstract

We present a new loss function, namely Wing loss, for robust facial landmark localisation with Convolutional Neural Networks (CNNs). We first compare and analyse different loss functions including L2, L1 and smooth L1. The analysis of these loss functions suggests that, for the training of a CNN-based localisation model, more attention should be paid to small and medium range errors. To this end, we design a piece-wise loss function. The new loss amplifies the impact of errors from the interval (-w, w) by switching from L1 loss to a modified logarithm function. To address the problem of under-representation of samples with large out-of-plane head rotations in the training set, we propose a simple but effective boosting strategy, referred to as pose-based data balancing. In particular, we deal with the data imbalance problem by duplicating the minority training samples and perturbing them by injecting random image rotation, bounding box translation and other data augmentation approaches. Last, the proposed approach is extended to create a two-stage framework for robust facial landmark localisation. The experimental results obtained on AFLW and 300W demonstrate the merits of the Wing loss function, and prove the superiority of the proposed method over the state-of-the-art approaches.

Bibliographical note

© 2018, The Author(s).

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations