Where is the Model Looking At?--Concentrate and Explain the Network Attention

Abstract

Image classification models have achieved satisfactory performance on many datasets, sometimes even better than human. However, The model attention is unclear since the lack of interpretability. This paper investigates the fidelity and interpretability of model attention. We propose an Explainable Attribute-based Multi-task (EAT) framework to concentrate the model attention on the discriminative image area and make the attention interpretable. We introduce attributes prediction to the multi-task learning network, helping the network to concentrate attention on the foreground objects. We generate attribute-based textual explanations for the network and ground the attributes on the image to show visual explanations. The multi-model explanation can not only improve user trust but also help to find the weakness of network and dataset. Our framework can be generalized to any basic model. We perform experiments on three datasets and five basic models. Results indicate that the EAT framework can give multi-modal explanations that interpret the network decision. The performance of several recognition approaches is improved by guiding network attention.

References in corpus (9)

• Striving for Simplicity: The All Convolutional Net
• An Overview of Multi-Task Learning in Deep Neural Networks
• Unsupervised Representation Learning by Predicting Image Rotations
• Hierarchical Question-Image Co-Attention for Visual Question Answering
• Improved Image Captioning via Policy Gradient optimization of SPIDEr
• Massively Multitask Networks for Drug Discovery
• RISE: Randomized Input Sampling for Explanation of Black-box Models
• Learning Multiple Tasks with Multilinear Relationship Networks
• Benchmarking Attribution Methods with Relative Feature Importance

Cited by in corpus (1)

• Deep Semantic-Visual Alignment for Zero-Shot Remote Sensing Image Scene Classification