# BOREx: Bayesian-Optimization--Based Refinement of Saliency Map for Image- and Video-Classification Models

arXiv: https://arxiv.org/abs/2210.17130 · HTML: https://mlsanity.com/paper/2210.17130/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 31 Oct 2022.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [Explanations can be manipulated and geometry is to blame](https://mlsanity.com/paper/1906.07983/) (2019)
- [Sanity Checks for Saliency Metrics](https://mlsanity.com/paper/1912.01451/) (2019)
- [Fooling Neural Network Interpretations via Adversarial Model Manipulation](https://mlsanity.com/paper/1902.02041/) (2019)
- [Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions](https://mlsanity.com/paper/1902.01078/) (2019)
- [Excitation Backprop for RNNs](https://mlsanity.com/paper/1711.06778/) (2017)
- [Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labels](https://mlsanity.com/paper/2010.08644/) (2020)
- [Evaluating Input Perturbation Methods for Interpreting CNNs and Saliency Map Comparison](https://mlsanity.com/paper/2101.10977/) (2021)
- [Play Fair: Frame Attributions in Video Models](https://mlsanity.com/paper/2011.12372/) (2020)
- [Black-Box Saliency Map Generation Using Bayesian Optimisation](https://mlsanity.com/paper/2001.11366/) (2020)
- [Visualizing Color-wise Saliency of Black-Box Image Classification Models](https://mlsanity.com/paper/2010.02468/) (2020)

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

- [Leaping Into Memories: Space-Time Deep Feature Synthesis](https://mlsanity.com/paper/2303.09941/) (2023)

## Abstract (arXiv)

Explaining a classification result produced by an image- and video-classification model is one of the important but challenging issues in computer vision. Many methods have been proposed for producing heat-map--based explanations for this purpose, including ones based on the white-box approach that uses the internal information of a model (e.g., LRP, Grad-CAM, and Grad-CAM++) and ones based on the black-box approach that does not use any internal information (e.g., LIME, SHAP, and RISE). We propose a new black-box method BOREx (Bayesian Optimization for Refinement of visual model Explanation) to refine a heat map produced by any method. Our observation is that a heat-map--based explanation can be seen as a prior for an explanation method based on Bayesian optimization. Based on this observation, BOREx conducts Gaussian process regression (GPR) to estimate the saliency of each pixel in a given image starting from the one produced by another explanation method. Our experiments statistically demonstrate that the refinement by BOREx improves low-quality heat maps for image- and video-classification results.