# Does Explainable Machine Learning Uncover the Black Box in Vision Applications?

arXiv: https://arxiv.org/abs/2112.09898 · HTML: https://mlsanity.com/paper/2112.09898/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 18 Dec 2021.

## Builds on (most cited first, 9 of 9)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [DDSP: Differentiable Digital Signal Processing](https://mlsanity.com/paper/2001.04643/) (2020)
- [Explainable Deep Learning: A Field Guide for the Uninitiated](https://mlsanity.com/paper/2004.14545/) (2020)
- [Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey](https://mlsanity.com/paper/1911.12116/) (2019)
- [Physics-based Deep Learning](https://mlsanity.com/paper/2109.05237/) (2021)
- [Explainable Machine Learning with Prior Knowledge: An Overview](https://mlsanity.com/paper/2105.10172/) (2021)

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

- [Interaction as Explanation: A User Interaction-based Method for Explaining Image Classification Models](https://mlsanity.com/paper/2404.09828/) (2024)

## Abstract (arXiv)

Machine learning (ML) in general and deep learning (DL) in particular has become an extremely popular tool in several vision applications (like object detection, super resolution, segmentation, object tracking etc.). Almost in parallel, the issue of explainability in ML (i.e. the ability to explain/elaborate the way a trained ML model arrived at its decision) in vision has also received fairly significant attention from various quarters. However, we argue that the current philosophy behind explainable ML suffers from certain limitations, and the resulting explanations may not meaningfully uncover black box ML models. To elaborate our assertion, we first raise a few fundamental questions which have not been adequately discussed in the corresponding literature. We also provide perspectives on how explainablity in ML can benefit by relying on more rigorous principles in the related areas.