Black-Box Saliency Map Generation Using Bayesian Optimisation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian OptimisationSimilar Papers 제목 키워드 기반
Bayesian Optimisation: Which Constraints Matter?
Bayesian optimisation has proven to be a powerful tool for expensive global black-box optimisation problems. In this paper, we propose new Bayesian optimisation variants of the popular Knowledge Gradient acquisition func…
MONGOOSE: Path-wise Smooth Bayesian Optimisation via Meta-learning
In Bayesian optimisation, we often seek to minimise the black-box objective functions that arise in real-world physical systems. A primary contributor to the cost of evaluating such black-box objective functions is often…
Bayesian OptimisationMeta-LearningHeteroscedastic Treed Bayesian Optimisation
Optimising black-box functions is important in many disciplines, such as tuning machine learning models, robotics, finance and mining exploration. Bayesian optimisation is a state-of-the-art technique for the global opti…
Bayesian OptimisationBIG-bench Machine LearningTrust Region-Based Bayesian Optimisation to Discover Diverse Solutions
Bayesian optimisation (BO) is a surrogate-based optimisation technique that efficiently solves expensive black-box functions with small evaluation budgets. Recent studies consider trust regions to improve the scalability…
An Empirical Study on Ensemble-Based Transfer Learning Bayesian Optimisation with Mixed Variable Types
Bayesian optimisation is a sample efficient method for finding a global optimum of expensive black-box objective functions. Historic datasets from related problems can be exploited to help improve performance of Bayesian…
Transfer Learning