Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance
This addresses the need for clearer and more detailed visual explanations of DNN decisions, which is an incremental improvement in the domain of model interpretability.
The paper tackles the problem of missing detailed descriptions in DNN decision explanations by proposing UCAG, a post-hoc framework that spatially scrutinizes input features based on model confidence, resulting in outperforming existing methods on metrics like deletion/insertion and pointing games.
Revealing the transparency of Deep Neural Networks (DNNs) has been widely studied to describe the decision mechanisms of network inner structures. In this paper, we propose a novel post-hoc framework, Unfold and Conquer Attribution Guidance (UCAG), which enhances the explainability of the network decision by spatially scrutinizing the input features with respect to the model confidence. Addressing the phenomenon of missing detailed descriptions, UCAG sequentially complies with the confidence of slices of the image, leading to providing an abundant and clear interpretation. Therefore, it is possible to enhance the representation ability of explanation by preserving the detailed descriptions of assistant input features, which are commonly overwhelmed by the main meaningful regions. We conduct numerous evaluations to validate the performance in several metrics: i) deletion and insertion, ii) (energy-based) pointing games, and iii) positive and negative density maps. Experimental results, including qualitative comparisons, demonstrate that our method outperforms the existing methods with the nature of clear and detailed explanations and applicability.