Improving Interpretability of Deep Neural Networks with Semantic Information

Citations Over TimeTop 10% of 2017 papers

Abstract

Interpretability of deep neural networks (DNNs) is essential since it enables users to understand the overall strengths and weaknesses of the models, conveys an understanding of how the models will behave in the future, and how to diagnose and correct potential problems. However, it is challenging to reason about what a DNN actually does due to its opaque or black-box nature. To address this issue, we propose a novel technique to improve the interpretability of DNNs by leveraging the rich semantic information embedded in human descriptions. By concentrating on the video captioning task, we first extract a set of semantically meaningful topics from the human descriptions that cover a wide range of visual concepts, and integrate them into the model with an interpretive loss. We then propose a prediction difference maximization algorithm to interpret the learned features of each neuron. Experimental results demonstrate its effectiveness in video captioning using the interpretable features, which can also be transferred to video action recognition. By clearly understanding the learned features, users can easily revise false predictions via a human-in-the-loop procedure.

Related Papers

• → Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing Their Input Gradients(2018)452 cited
• → OSCAR and ActivityNet: an Image Captioning model can effectively learn a Video Captioning dataset(2021)1 cited
• → Video Captioning via Hierarchical Reinforcement Learning(2017)22 cited
• → Improving the Adversarial Robustness and Interpretability of Deep Neural\n Networks by Regularizing their Input Gradients(2017)4 cited
• → Improving Interpretability via Regularization of Neural Activation Sensitivity(2022)2 cited