# Enhancing Visual Feature Attribution via Weighted Integrated Gradients

arXiv: https://arxiv.org/abs/2505.03201 · HTML: https://mlsanity.com/paper/2505.03201/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 6 May 2025.

## Builds on (most cited first, 11 of 11)

- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Understanding Neural Networks through Representation Erasure](https://mlsanity.com/paper/1612.08220/) (2016)
- [Attribution in Scale and Space](https://mlsanity.com/paper/2004.03383/) (2020)
- [IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients](https://mlsanity.com/paper/2303.14242/) (2023)
- [Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics](https://mlsanity.com/paper/2409.16756/) (2024)
- [Toward Understanding the Disagreement Problem in Neural Network Feature Attribution](https://mlsanity.com/paper/2404.11330/) (2024)
- [Towards credible visual model interpretation with path attribution](https://mlsanity.com/paper/2305.14395/) (2023)
- [An Efficient Ensemble Explainable AI (XAI) Approach for Morphed Face Detection](https://mlsanity.com/paper/2304.14509/) (2023)

## Abstract (arXiv)

Integrated Gradients (IG) is a widely used attribution method in explainable AI, particularly in computer vision applications where reliable feature attribution is essential. A key limitation of IG is its sensitivity to the choice of baseline (reference) images. Multi-baseline extensions such as Expected Gradients (EG) assume uniform weighting over baselines, implicitly treating all baseline images as equally informative. In high-dimensional vision models, this assumption often leads to noisy or unstable explanations. This paper proposes Weighted Integrated Gradients (WG), a principled approach that evaluates and weights baselines to enhance attribution reliability. WG introduces an unsupervised criterion for baseline suitability, enabling adaptive selection and weighting of baselines on a per-input basis. The method preserves the core axiomatic properties of IG in a generalized weighted-baseline form. Under an expected, proxy-based fitness--relevance monotonicity assumption, WG provides a probabilistic justification for assigning larger weights to more informative baselines. Experiments on commonly used image datasets and models show that WG improves over EG under our protocol, with up to 36% gains across evaluated convolutional and Transformer architectures. These gains come with additional fitness-evaluation cost, so WG should be viewed as an attribution-fidelity trade-off rather than a faster alternative to EG. By moving beyond the assumption that all baselines contribute equally, Weighted Integrated Gradients offers a clearer and more reliable approach to explaining computer-vision models, improving both understanding and practical usability in explainable AI.