Timezone: »

 
Towards Better Visual Explanations for Deep ImageClassifiers
Agnieszka Grabska-Barwinska · Amal Rannen-Triki · Omar Rivasplata · András György
Event URL: https://openreview.net/forum?id=-iFcfENgxaM »

Understanding and explaining the decisions of neural networks is of great importance, for safe deployment as well as for legal reasons.In this paper, we consider visual explanations for deep image classifiers that are both informative and understandable by humans. Motivated by the recent FullGrad method, we find that bringing information from multiple layers is very effective in producing explanations. Based on this observation, we propose a new method, DeepMaps, that combines information from hidden activities. We show that our method outranks alternative explanations with respect to metrics established in the literature, which are based on pixel perturbations. While these evaluations are based on changes in the class scores, we propose to directly consider the change in the network's decisions. Noting that perturbation-based metrics can fail to distinguish random explanations from sensible ones, we propose to measure the quality of a given explanation by comparing it to explanations for randomly selected other images. We demonstrate through experiments that DeepMaps outperforms existing methods according to the resulting evaluation metrics as well.

Author Information

Agnieszka Grabska-Barwinska (Google DeepMind)
Amal Rannen-Triki (DeepMind)
Omar Rivasplata (IMSS UCL)

My top-level areas of interest are statistical learning theory, machine learning, probability and statistics. These days I am very interested in deep learning and reinforcement learning. I am affiliated with the Institute for Mathematical and Statistical Sciences, University College London, hosted by the Department of Statistical Science as a Senior Research Fellow. Before my current post I was for a few months at UCL Department of Mathematics, and previously I was for a few years at UCL Department of Computer Science where I did research studies (machine learning) sponsored by DeepMind and in parallel with these studies I was a research scientist intern at DeepMind for three years. Back in the day I studied undergraduate maths (BSc 2000, Pontificia Universidad Católica del Perú) and graduate maths (MSc 2005, PhD 2012, University of Alberta). I've lived in Peru, in Canada, and now I'm based in the UK.

András György (DeepMind)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors