Conference material: "Proceedings of the International Conference on Computer Graphics and Vision “Graphicon”"
Authors:Penkin M.A., Khvostikov A.V., Krylov A.S.
Optimal Input Scale Transformation Search for Deep Classification Neural Networks
The paper deals with problem of optimal input scale search for deep classification neural networks. It is shown that state-of-the-art deep neural networks are not stable to input image scale, leading to quality degradation. The paper demonstrates relevance of the topic on classical image classification DL-pipeline. Unlike previous researchers, who aim to build entire complex invariant neural nets, we claim that computing optimal input transformations (e.g. scale) is a more perspective way for successful neural networks real-life applications. Thus, a new scale search algorithm for DL image classification is proposed in the paper, based on empirical hierarchical analysis of activation values.
Image scale estimation, Deep learning, Image classification, Medical imaging