Kaifeng Zou

Kaifeng Zou, Sylvain Faisan, Fabrice Heitz et al.

By highlighting the regions of the input image that contribute the most to the decision, saliency maps have become a popular method to make neural networks interpretable. In medical imaging, they are particularly well-suited to explain neural networks in the context of abnormality localization. However, from our experiments, they are less suited to classification problems where the features that allow to distinguish between the different classes are spatially correlated, scattered and definitely non-trivial. In this paper we thus propose a new paradigm for better interpretability. To this end we provide the user with relevant and easily interpretable information so that he can form his own opinion. We use Disentangled Variational Auto-Encoders which latent representation is divided into two components: the non-interpretable part and the disentangled part. The latter accounts for the categorical variables explicitly representing the different classes of interest. In addition to providing the class of a given input sample, such a model offers the possibility to transform the sample from a given class to a sample of another class, by modifying the value of the categorical variables in the latent representation. This paves the way to easier interpretation of class differences. We illustrate the relevance of this approach in the context of automatic sex determination from hip bones in forensic medicine. The features encoded by the model, that distinguish the different classes were found to be consistent with expert knowledge.

Hyewon Seo, Kaifeng Zou, Frederic Cordier

Skin dynamics contributes to the enriched realism of human body models in rendered scenes. Traditional methods rely on physics-based simulations to accurately reproduce the dynamic behavior of soft tissues. Due to the model complexity and thus the heavy computation, however, they do not directly offer practical solutions to domains where real-time performance is desirable. The quality shapes obtained by physics-based simulations are not fully exploited by example-based or more recent datadriven methods neither, with most of them having focused on the modeling of static skin shapes by leveraging quality data. To address these limitations, we present a learningbased method for dynamic skin deformation. At the core of our work is a recurrent neural network that learns to predict the nonlinear, dynamics-dependent shape change over time from pre-existing mesh deformation sequence data. Our network also learns to predict the variation of skin dynamics across different individuals with varying body shapes. After training the network delivers realistic, high-quality skin dynamics that is specific to a person in a real-time course. We obtain results that significantly saves the computational time, while maintaining comparable prediction quality compared to state-of-the-art results.