# Black-Box Saliency Map Generation Using Bayesian Optimisation

arXiv: https://arxiv.org/abs/2001.11366 · HTML: https://mlsanity.com/paper/2001.11366/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jan 2020.

## Built on by (most cited first, 3 of 3)

- [Leaping Into Memories: Space-Time Deep Feature Synthesis](https://mlsanity.com/paper/2303.09941/) (2023)
- [BOREx: Bayesian-Optimization--Based Refinement of Saliency Map for Image- and Video-Classification Models](https://mlsanity.com/paper/2210.17130/) (2022)
- [Mitigating Pretraining-Induced Attention Asymmetry in 2D+ Electron Microscopy Image Segmentation](https://mlsanity.com/paper/2505.14105/) (2025)

## Abstract (arXiv)

Saliency maps are often used in computer vision to provide intuitive interpretations of what input regions a model has used to produce a specific prediction. A number of approaches to saliency map generation are available, but most require access to model parameters. This work proposes an approach for saliency map generation for black-box models, where no access to model parameters is available, using a Bayesian optimisation sampling method. The approach aims to find the global salient image region responsible for a particular (black-box) model's prediction. This is achieved by a sampling-based approach to model perturbations that seeks to localise salient regions of an image to the black-box model. Results show that the proposed approach to saliency map generation outperforms grid-based perturbation approaches, and performs similarly to gradient-based approaches which require access to model parameters.