Facial Landmark Correlation Analysis
This work addresses the challenge of improving facial landmark detection by leveraging correlation analysis, offering incremental advancements in model interpretation and annotation efficiency for computer vision applications.
The authors tackled the problem of understanding inherent relationships among facial landmarks by analyzing their correlations using Canonical Correlation Analysis (CCA), revealing strong correlations in current benchmarks and applying this to gain insights into model predictions and enable few-shot learning to reduce annotation effort.
We present a facial landmark position correlation analysis as well as its applications. Although numerous facial landmark detection methods have been presented in the literature, few of them explicitly take into account the inherent relationship among landmarks. To reveal and interpret this relationship, we propose to analyze landmark correlation by using Canonical Correlation Analysis~(CCA). We experimentally show that the dense facial landmark annotations in current benchmarks are strongly correlated. We propose two applications based on this analysis. First, by analyzing the landmark correlation, we gain some interesting insights into the predictions of different landmark detection models (including random forests model and CNN models). We also demonstrate how CNNs progressively learn to predict facial landmarks. Second, we propose a few-shot learning method that allows to considerably reduce the manual effort for dense landmark annotation.