3FabRec: Fast Few-shot Face alignment by Reconstruction

by   Bjoern Browatzki, et al.

Current supervised frameworks for facial landmark detection require a large amount of training data and due to the massive number of parameters may suffer from overfitting to the specific datasets. We introduce a semi-supervised method in which the crucial idea is to first generate implicit knowledge about the face appearance shape from the large amounts of unlabeled images of faces available today. In a first, unsupervised stage, we train an adversarial autoencoder to reconstruct faces via a low-dimensional, latent face-representation vector. In a second, supervised stage, we augment the generator-decoder pipeline with interleaved transfer layers in order to both reconstruct the face and a probabilistic landmark heatmap. We show that this framework (3FabRec) achieves state-of-the-art performance on popular benchmarks, such as 300-W, AFLW, and WLFW. Importantly, due to the power of the implicit face representation, our framework achieves impressive landmark localization accuracy from only a few percent of training data to as low as even 10 images. As the interleaved layers only add a small number of parameters to the encoder, inference runs at several hundred FPS on a GPU.


page 1

page 3

page 6

page 7

page 11

page 13


MobileFAN: Transferring Deep Hidden Representation for Face Alignment

Facial landmark detection is a crucial prerequisite for many face analys...

Robust Facial Landmark Detection via Aggregation on Geometrically Manipulated Faces

In this work, we present a practical approach to the problem of facial l...

Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Translation

Facial landmark detection, or face alignment, is a fundamental task that...

Few-Shot Model Adaptation for Customized Facial Landmark Detection, Segmentation, Stylization and Shadow Removal

Despite excellent progress has been made, the performance of deep learni...

Spoof Face Detection Via Semi-Supervised Adversarial Training

Face spoofing causes severe security threats in face recognition systems...

Multi-Domain Multi-Definition Landmark Localization for Small Datasets

We present a novel method for multi image domain and multi-landmark defi...

Multi-Modal Face Stylization with a Generative Prior

In this work, we introduce a new approach for artistic face stylization....

Please sign up or login with your details

Forgot password? Click here to reset