How You See Me
This addresses the interpretability issue for researchers and practitioners using CNNs, but it appears incremental as it builds on existing math without major methodological breakthroughs.
The paper tackles the problem of understanding how Convolutional Neural Networks (CNNs) interpret images by proposing an algorithm that backtracks important pixels for predictions without additional training, though no concrete performance numbers are provided.
Convolution Neural Networks is one of the most powerful tools in the present era of science. There has been a lot of research done to improve their performance and robustness while their internal working was left unexplored to much extent. They are often defined as black boxes that can map non-linear data very effectively. This paper tries to show how CNN has learned to look at an image. The proposed algorithm exploits the basic math of CNN to backtrack the important pixels it is considering to predict. This is a simple algorithm which does not involve any training of its own over a pre-trained CNN which can classify.