Rotation-Invariant Gait Identification with Quaternion Convolutional Neural Networks
This addresses a robustness issue in accelerometric gait-based identification for users with varying device orientations, but it is incremental as it builds on existing CNN methods with a novel architectural twist.
The paper tackled the problem of gait identification systems being sensitive to unseen device orientations by introducing a Quaternion CNN that is inherently rotation-equivariant and invariant. The result was a significant performance improvement over traditional CNNs in multi-user rotation-invariant gait classification, though no concrete numbers were provided.
A desireable property of accelerometric gait-based identification systems is robustness to new device orientations presented by users during testing but unseen during the training phase. However, traditional Convolutional neural networks (CNNs) used in these systems compensate poorly for such transformations. In this paper, we target this problem by introducing Quaternion CNN, a network architecture which is intrinsically layer-wise equivariant and globally invariant under 3D rotations of an array of input vectors. We show empirically that this network indeed significantly outperforms a traditional CNN in a multi-user rotation-invariant gait classification setting .Lastly, we demonstrate how the kernels learned by this QCNN can also be visualized as basis-independent but origin- and chirality-dependent trajectory fragments in the euclidean space, thus yielding a novel mode of feature visualization and extraction.