# XRAI: Better Attributions Through Regions

arXiv: https://arxiv.org/abs/1906.02825 · HTML: https://mlsanity.com/paper/1906.02825/

## Key facts

- Cited by 116 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2019.

## Built on by (most cited first, 30 of 116)

- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [Benchmarking and Survey of Explanation Methods for Black Box Models](https://mlsanity.com/paper/2102.13076/) (2021)
- [Algorithms to estimate Shapley value feature attributions](https://mlsanity.com/paper/2207.07605/) (2022)
- [Guided Integrated Gradients: An Adaptive Path Method for Removing Noise](https://mlsanity.com/paper/2106.09788/) (2021)
- [What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods](https://mlsanity.com/paper/2112.04417/) (2021)
- [Impossibility Theorems for Feature Attribution](https://mlsanity.com/paper/2212.11870/) (2022)
- [Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis](https://mlsanity.com/paper/2111.04138/) (2021)
- [FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion](https://mlsanity.com/paper/2406.08603/) (2024)
- [Group-CAM: Group Score-Weighted Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/2103.13859/) (2021)
- [Gradient based Feature Attribution in Explainable AI: A Technical Review](https://mlsanity.com/paper/2403.10415/) (2024)
- [Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure](https://mlsanity.com/paper/2206.06219/) (2022)
- [LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity](https://mlsanity.com/paper/2404.03214/) (2024)
- [CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency](https://mlsanity.com/paper/2106.10649/) (2021)
- [Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks](https://mlsanity.com/paper/2401.06654/) (2024)
- [Best of both worlds: local and global explanations with human-understandable concepts](https://mlsanity.com/paper/2106.08641/) (2021)
- [GLIME: General, Stable and Local LIME Explanation](https://mlsanity.com/paper/2311.15722/) (2023)
- [CoRTX: Contrastive Framework for Real-time Explanation](https://mlsanity.com/paper/2303.02794/) (2023)
- [Evaluating Feature Attribution Methods in the Image Domain](https://mlsanity.com/paper/2202.12270/) (2022)
- [Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification](https://mlsanity.com/paper/2208.08741/) (2022)
- [Visual Explanations via Iterated Integrated Attributions](https://mlsanity.com/paper/2310.18585/) (2023)
- [Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders](https://mlsanity.com/paper/2203.10417/) (2022)
- [A Game-Theoretic Taxonomy of Visual Concepts in DNNs](https://mlsanity.com/paper/2106.10938/) (2021)
- [Attribution-based XAI Methods in Computer Vision: A Review](https://mlsanity.com/paper/2211.14736/) (2022)
- [IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients](https://mlsanity.com/paper/2303.14242/) (2023)
- [Towards Better Explanations for Object Detection](https://mlsanity.com/paper/2306.02744/) (2023)
- [Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation](https://mlsanity.com/paper/2103.14332/) (2021)
- [IG2: Integrated Gradient on Iterative Gradient Path for Feature Attribution](https://mlsanity.com/paper/2406.10852/) (2024)
- [Saliency Cards: A Framework to Characterize and Compare Saliency Methods](https://mlsanity.com/paper/2206.02958/) (2022)
- [Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Survey](https://mlsanity.com/paper/2405.01636/) (2024)
- [Data Augmentation for Image Classification using Generative AI](https://mlsanity.com/paper/2409.00547/) (2024)

## Abstract (arXiv)

Saliency methods can aid understanding of deep neural networks. Recent years have witnessed many improvements to saliency methods, as well as new ways for evaluating them. In this paper, we 1) present a novel region-based attribution method, XRAI, that builds upon integrated gradients (Sundararajan et al. 2017), 2) introduce evaluation methods for empirically assessing the quality of image-based saliency maps (Performance Information Curves (PICs)), and 3) contribute an axiom-based sanity check for attribution methods. Through empirical experiments and example results, we show that XRAI produces better results than other saliency methods for common models and the ImageNet dataset.