Facial Landmark Detection with Tweaked Convolutional Neural Networks
This improves facial landmark detection for applications like face verification, though it appears incremental as it builds on existing CNN methods.
The paper tackled facial landmark detection by introducing a Tweaked CNN (TCNN) that applies differential processing based on facial alignment, achieving state-of-the-art results on standard benchmarks with wide performance margins.
We present a novel convolutional neural network (CNN) design for facial landmark coordinate regression. We examine the intermediate features of a standard CNN trained for landmark detection and show that features extracted from later, more specialized layers capture rough landmark locations. This provides a natural means of applying differential treatment midway through the network, tweaking processing based on facial alignment. The resulting Tweaked CNN model (TCNN) harnesses the robustness of CNNs for landmark detection, in an appearance-sensitive manner without training multi-part or multi-scale models. Our results on standard face landmark detection and face verification benchmarks show TCNN to surpasses previously published performances by wide margins.