Interspecies Knowledge Transfer for Facial Keypoint Detection
arXiv:1704.04023
Abstract
We present a method for localizing facial keypoints on animals by transferring knowledge gained from human faces. Instead of directly finetuning a network trained to detect keypoints on human faces to animal faces (which is sub-optimal since human and animal faces can look quite different), we propose to first adapt the animal images to the pre-trained human detection network by correcting for the differences in animal and human face shape. We first find the nearest human neighbors for each animal image using an unsupervised shape matching method. We use these matches to train a thin plate spline warping network to warp each animal face to look more human-like. The warping network is then jointly finetuned with a pre-trained human facial keypoint detection network using an animal dataset. We demonstrate state-of-the-art results on both horse and sheep facial keypoint detection, and significant improvement over simple finetuning, especially when training data is scarce. Additionally, we present a new dataset with 3717 images with horse face and facial keypoint annotations.
CVPR 2017 Camera Ready
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- What makes ImageNet good for transfer learning?
- Do We Really Need to Collect Millions of Faces for Effective Face Recognition?
- Unconstrained Facial Landmark Localization with Backbone-Branches Fully-Convolutional Networks
- Robust Face Alignment Using a Mixture of Invariant Experts
- A Recurrent Encoder-Decoder Network for Sequential Face Alignment
- Facial Landmark Detection with Tweaked Convolutional Neural Networks
- Face Alignment Assisted by Head Pose Estimation
- End-to-End Localization and Ranking for Relative Attributes
- Constrained Joint Cascade Regression Framework for Simultaneous Facial Action Unit Recognition and Facial Landmark Detection