# A general approach to compute the relevance of middle-level input features

arXiv: https://arxiv.org/abs/2010.08639 · HTML: https://mlsanity.com/paper/2010.08639/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2020.

## Built on by (most cited first, 2 of 2)

- [Exploiting auto-encoders and segmentation methods for middle-level explanations of image classification systems](https://mlsanity.com/paper/2106.05037/) (2021)
- [The Impact of Stochasticity on the Rashomon Effect in Machine Learning](https://mlsanity.com/paper/2609.32934/) (2026)

## Abstract (arXiv)

This work proposes a novel general framework, in the context of eXplainable Artificial Intelligence (XAI), to construct explanations for the behaviour of Machine Learning (ML) models in terms of middle-level features. One can isolate two different ways to provide explanations in the context of XAI: low and middle-level explanations. Middle-level explanations have been introduced for alleviating some deficiencies of low-level explanations such as, in the context of image classification, the fact that human users are left with a significant interpretive burden: starting from low-level explanations, one has to identify properties of the overall input that are perceptually salient for the human visual system. However, a general approach to correctly evaluate the elements of middle-level explanations with respect ML model responses has never been proposed in the literature.