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.