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

Source: [Where is the Model Looking At?--Concentrate and Explain the Network Attention](<https://www.sota2.com/research/paper/68fa68651e209131cea1bc3b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:36:00.183Z

Authors: Wenjia Xu, Jiuniu Wang, Yang Wang, Guangluan Xu, Wei Dai, Yirong Wu

Published: 2020-09-29T08:36:18.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2009.13862>)

[PDF](<https://arxiv.org/pdf/2009.13862.pdf>)
