# Accurate Explanation Model for Image Classifiers using Class Association Embedding

arXiv: https://arxiv.org/abs/2406.07961 · HTML: https://mlsanity.com/paper/2406.07961/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 78 references that are in the map.
- First posted on arXiv 12 Jun 2024.

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification](https://mlsanity.com/paper/2107.02314/) (2021)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (2017)
- [Distilling a Neural Network Into a Soft Decision Tree](https://mlsanity.com/paper/1711.09784/) (2017)
- [GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2001.06216/) (2020)
- [Full-Gradient Representation for Neural Network Visualization](https://mlsanity.com/paper/1905.00780/) (2019)
- [Explaining Image Classifiers by Counterfactual Generation](https://mlsanity.com/paper/1807.08024/) (2018)
- [Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model](https://mlsanity.com/paper/1511.01644/) (2015)
- [Explaining in Style: Training a GAN to explain a classifier in StyleSpace](https://mlsanity.com/paper/2104.13369/) (2021)
- [Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability](https://mlsanity.com/paper/1910.06358/) (2019)
- [Explainable deep learning models in medical image analysis](https://mlsanity.com/paper/2005.13799/) (2020)
- [XAI for Transformers: Better Explanations through Conservative Propagation](https://mlsanity.com/paper/2202.07304/) (2022)
- [Which Neural Net Architectures Give Rise To Exploding and Vanishing Gradients?](https://mlsanity.com/paper/1801.03744/) (2018)
- [Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation](https://mlsanity.com/paper/1710.06169/) (2017)
- [Shapley Flow: A Graph-based Approach to Interpreting Model Predictions](https://mlsanity.com/paper/2010.14592/) (2020)
- [STEEX: Steering Counterfactual Explanations with Semantics](https://mlsanity.com/paper/2111.09094/) (2021)

## Built on by (most cited first, 6 of 6)

- [Prompt Categories Cluster for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2412.13823/) (2024)
- [A Weakly Supervised and Globally Explainable Learning Framework for Brain Tumor Segmentation](https://mlsanity.com/paper/2408.01191/) (2024)
- [Enhancing Interpretability for Vision Models via Shapley Value Optimization](https://mlsanity.com/paper/2512.14354/) (2025)
- [Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion](https://mlsanity.com/paper/2504.03135/) (2025)
- [MSA-UNet3+: Multi-Scale Attention UNet3+ with New Supervised Prototypical Contrastive Loss for Coronary DSA Image Segmentation](https://mlsanity.com/paper/2504.05184/) (2025)
- [Contrastive Prompt Clustering for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2508.17009/) (2025)

## Abstract (arXiv)

Image classification is a primary task in data analysis where explainable models are crucially demanded in various applications. Although amounts of methods have been proposed to obtain explainable knowledge from the black-box classifiers, these approaches lack the efficiency of extracting global knowledge regarding the classification task, thus is vulnerable to local traps and often leads to poor accuracy. In this study, we propose a generative explanation model that combines the advantages of global and local knowledge for explaining image classifiers. We develop a representation learning method called class association embedding (CAE), which encodes each sample into a pair of separated class-associated and individual codes. Recombining the individual code of a given sample with altered class-associated code leads to a synthetic real-looking sample with preserved individual characters but modified class-associated features and possibly flipped class assignments. A building-block coherency feature extraction algorithm is proposed that efficiently separates class-associated features from individual ones. The extracted feature space forms a low-dimensional manifold that visualizes the classification decision patterns. Explanation on each individual sample can be then achieved in a counter-factual generation manner which continuously modifies the sample in one direction, by shifting its class-associated code along a guided path, until its classification outcome is changed. We compare our method with state-of-the-art ones on explaining image classification tasks in the form of saliency maps, demonstrating that our method achieves higher accuracies. The code is available at https://github.com/xrt11/XAI-CODE.