3FabRec: Fast Few-shot Face alignment by Reconstruction

24 Nov 2019  ·  Bjoern Browatzki, Christian Wallraven ·

Current supervised methods for facial landmark detection require a large amount of training data and may suffer from overfitting to specific datasets due to the massive number of parameters. We introduce a semi-supervised method in which the crucial idea is to first generate implicit face knowledge from the large amounts of unlabeled images of faces available today. In a first, completely unsupervised stage, we train an adversarial autoencoder to reconstruct faces via a low-dimensional face embedding. In a second, supervised stage, we interleave the decoder with transfer layers to retask the generation of color images to the prediction of landmark heatmaps. Our framework (3FabRec) achieves state-of-the-art performance on several common benchmarks and, most importantly, is able to maintain impressive accuracy on extremely small training sets down to as few as 10 images. As the interleaved layers only add a low amount of parameters to the decoder, inference runs at several hundred FPS on a GPU.

PDF Abstract

Results from the Paper


Ranked #4 on Face Alignment on AFLW-19 (NME_box (%, Full) metric, using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Face Alignment 300W 3FabRec NME_inter-ocular (%, Full) 3.82 # 33
NME_inter-ocular (%, Common) 3.36 # 36
NME_inter-ocular (%, Challenge) 5.74 # 33
Face Alignment AFLW-19 3FabRec NME_box (%, Full) 1.84 # 4

Methods