Dilated Convolutional Neural Networks for Sequential Manifold-Valued Data

Abstract

Efforts are underway to study ways via which the power of deep neural networks can be extended to non-standard data types such as structured data (e.g., graphs) or manifold-valued data (e.g., unit vectors or special matrices). Often, sizable empirical improvements are possible when the geometry of such data spaces are incorporated into the design of the model, architecture, and the algorithms. Motivated by neuroimaging applications, we study formulations where the data are sequential manifold-valued measurements. This case is common in brain imaging, where the samples correspond to symmetric positive definite matrices or orientation distribution functions. Instead of a recurrent model which poses computational/technical issues, and inspired by recent results showing the viability of dilated convolutional models for sequence prediction, we develop a dilated convolutional neural network architecture for this task. On the technical side, we show how the modules needed in our network can be derived while explicitly taking the Riemannian manifold structure into account. We show how the operations needed can leverage known results for calculating the weighted Fréchet Mean (wFM). Finally, we present scientific results for group difference analysis in Alzheimer's disease (AD) where the groups are derived using AD pathology load: here the model finds several brain fiber bundles that are related to AD even when the subjects are all still cognitively healthy.

Deep Geometrical Learning for Alzheimer’s Disease Progression Modeling

“…We then set the ManifoldDCNN and SPDSRU model output channels to 16 and 8, resulting in 16× 16 and 8 × 8 covariance matrix dimensions, respectively. We adhered to model settings established in a previous study [20]. An Adam optimizer trained the ManifoldDCNN and SPDSRU models with 10 −3 and 5 × 10 −3 learning rates, respectively, and ℓ 2 regularization with a weight coefficient of 10 −4 .…”

“…For instance, SPDSRU [19] fabricates a statistical recurrent network that harnesses non-Euclidean temporal, longitudinal, and ordered data. Alternatively, ManifoldDCNN [20] redefines dilated Fig. 2.…”

“…Unlike conventional RNNs that operate on Euclidean space, the RNN-based model variant with a gating mechanism (or the Riemannian manifold GRU [RGRU] [11]) operates on Riemannian manifold space for more flexibility when modeling temporal complex data dynamics [19], [20], [27]. RGRU embodies three components:…”

Attention-aided lightweight networks friendly to smart weeding robot hardware resources for crops and weeds semantic segmentation

“…In weed-rich areas, occlusions and overlaps between crops and weeds highly affect target detection accuracy, making it unsuitable for weed problemsolving. Regarding pixel-by-pixel semantic segmentation of crops and weeds, (You et al, 2020) have made improvements to CNN-based models by employing techniques such as extended convolution (Zhen et al, 2019) and multiscale approaches (Chen et al, 2017b). These efforts have led to consistent improvements in segmentation accuracy.…”

Hybrid Time-Series Framework for Daily-Based PM2.5 Forecasting

“…In [43], Zhen et al presented a dilated CNN approach for sequence prediction. The approach utilizes dilation factors to extend the receptive fields and introduces residual connections to form a deeper network.…”