3FabRec: Fast Few-shot Face alignment by Reconstruction
This addresses the need for efficient and data-efficient facial alignment in computer vision, offering a practical solution for applications with limited labeled data.
The paper tackles the problem of facial landmark detection requiring large datasets by introducing a semi-supervised method that first learns face embeddings from unlabeled images and then adapts to predict landmarks with minimal labeled data, achieving state-of-the-art performance on benchmarks and maintaining high accuracy with as few as 10 training images.
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.