Deep Features Analysis with Attention Networks
This addresses the challenge of model interpretability in computer vision, which is an incremental advancement for researchers and practitioners.
The paper tackles the problem of interpreting deep neural network models by proposing a novel attention-based method to analyze the relationship between classification accuracy and attention heatmaps, showing that improved classifiers can be interpreted through these heatmaps.
Deep neural network models have recently draw lots of attention, as it consistently produce impressive results in many computer vision tasks such as image classification, object detection, etc. However, interpreting such model and show the reason why it performs quite well becomes a challenging question. In this paper, we propose a novel method to interpret the neural network models with attention mechanism. Inspired by the heatmap visualization, we analyze the relation between classification accuracy with the attention based heatmap. An improved attention based method is also included and illustrate that a better classifier can be interpreted by the attention based heatmap.