Boosting Deep Neural Networks with Geometrical Prior Knowledge: A Survey
It provides a concise overview for researchers and practitioners in machine learning and computer vision, but is incremental as it surveys existing approaches rather than introducing new methods.
This survey addresses the challenges of data inefficiency and lack of interpretability in deep neural networks by exploring methods to incorporate geometrical prior knowledge, such as symmetry transformations, to improve data efficiency and interpretability in tasks like 3D object detection for autonomous driving.
Deep Neural Networks achieve state-of-the-art results in many different problem settings by exploiting vast amounts of training data. However, collecting, storing and - in the case of supervised learning - labelling the data is expensive and time-consuming. Additionally, assessing the networks' generalization abilities or predicting how the inferred output changes under input transformations is complicated since the networks are usually treated as a black box. Both of these problems can be mitigated by incorporating prior knowledge into the neural network. One promising approach, inspired by the success of convolutional neural networks in computer vision tasks, is to incorporate knowledge about symmetric geometrical transformations of the problem to solve that affect the output in a predictable way. This promises an increased data efficiency and more interpretable network outputs. In this survey, we try to give a concise overview about different approaches that incorporate geometrical prior knowledge into neural networks. Additionally, we connect those methods to 3D object detection for autonomous driving, where we expect promising results when applying those methods.