Paper ID: 2310.14045

Training Image Derivatives: Increased Accuracy and Universal Robustness

Vsevolod I. Avrutskiy

Derivative training is a known method that significantly improves the accuracy of neural networks in some low-dimensional applications. In this paper, a similar improvement is obtained for an image analysis problem: reconstructing the vertices of a cube from its image. By training the derivatives with respect to the 6 degrees of freedom of the cube, we obtain 25 times more accurate results for noiseless inputs. The derivatives also offer insight into the robustness problem, which is currently understood in terms of two types of network vulnerabilities. The first type involves small perturbations that dramatically change the output, and the second type relates to substantial image changes that the network erroneously ignores. Defense against each is possible, but safeguarding against both while maintaining the accuracy defies conventional training methods. The first type is analyzed using the network's gradient, while the second relies on human input evaluation, serving as an oracle substitute. For the task at hand, the nearest neighbor oracle can be defined and expanded into Taylor series using image derivatives. This allows for a robustness analysis that unifies both types of vulnerabilities and enables training where accuracy and universal robustness are limited only by network capacity.

Submitted: Oct 21, 2023