# IMACS: Image Model Attribution Comparison Summaries

arXiv: https://arxiv.org/abs/2201.11196 · HTML: https://mlsanity.com/paper/2201.11196/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 26 Jan 2022.

## Builds on (most cited first, 22 of 22)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Towards Accountability for Machine Learning Datasets: Practices from Software Engineering and Infrastructure](https://mlsanity.com/paper/2010.13561/) (2020)
- [REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets](https://mlsanity.com/paper/2004.07999/) (2020)
- [XRAI: Better Attributions Through Regions](https://mlsanity.com/paper/1906.02825/) (2019)
- [Guided Integrated Gradients: An Adaptive Path Method for Removing Noise](https://mlsanity.com/paper/2106.09788/) (2021)
- [Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches](https://mlsanity.com/paper/1912.05100/) (2019)
- [Image Counterfactual Sensitivity Analysis for Detecting Unintended Bias](https://mlsanity.com/paper/1906.06439/) (2019)
- [Boxer: Interactive Comparison of Classifier Results](https://mlsanity.com/paper/2004.07964/) (2020)
- [ConfusionFlow: A model-agnostic visualization for temporal analysis of classifier confusion](https://mlsanity.com/paper/1910.00969/) (2019)
- [High Dimensional Model Explanations: an Axiomatic Approach](https://mlsanity.com/paper/2006.08969/) (2020)
- [Model LineUpper: Supporting Interactive Model Comparison at Multiple Levels for AutoML](https://mlsanity.com/paper/2104.04375/) (2021)
- [DFSeer: A Visual Analytics Approach to Facilitate Model Selection for Demand Forecasting](https://mlsanity.com/paper/2005.03244/) (2020)

## Built on by (most cited first, 1 of 1)

- [Understanding Text Classification Data and Models Using Aggregated Input Salience](https://mlsanity.com/paper/2211.05485/) (2022)

## Abstract (arXiv)

Developing a suitable Deep Neural Network (DNN) often requires significant iteration, where different model versions are evaluated and compared. While metrics such as accuracy are a powerful means to succinctly describe a model's performance across a dataset or to directly compare model versions, practitioners often wish to gain a deeper understanding of the factors that influence a model's predictions. Interpretability techniques such as gradient-based methods and local approximations can be used to examine small sets of inputs in fine detail, but it can be hard to determine if results from small sets generalize across a dataset. We introduce IMACS, a method that combines gradient-based model attributions with aggregation and visualization techniques to summarize differences in attributions between two DNN image models. More specifically, IMACS extracts salient input features from an evaluation dataset, clusters them based on similarity, then visualizes differences in model attributions for similar input features. In this work, we introduce a framework for aggregating, summarizing, and comparing the attribution information for two models across a dataset; present visualizations that highlight differences between 2 image classification models; and show how our technique can uncover behavioral differences caused by domain shift between two models trained on satellite images.