Iterative and Adaptive Sampling with Spatial Attention for Black-Box Model Explanations

by   Bhavan Vasu, et al.

Deep neural networks have achieved great success in many real-world applications, yet it remains unclear and difficult to explain their decision-making process to an end-user. In this paper, we address the explainable AI problem for deep neural networks with our proposed framework, named IASSA, which generates an importance map indicating how salient each pixel is for the model's prediction with an iterative and adaptive sampling module. We employ an affinity matrix calculated on multi-level deep learning features to explore long-range pixel-to-pixel correlation, which can shift the saliency values guided by our long-range and parameter-free spatial attention. Extensive experiments on the MS-COCO dataset show that our proposed approach matches or exceeds the performance of state-of-the-art black-box explanation methods.


page 1

page 3

page 6

page 7

page 8


RISE: Randomized Input Sampling for Explanation of Black-box Models

Deep neural networks are increasingly being used to automate data analys...

MFPP: Morphological Fragmental Perturbation Pyramid for Black-Box Model Explanations

With the increasing popularity of deep neural networks (DNNs), it has re...

PICA: A Pixel Correlation-based Attentional Black-box Adversarial Attack

The studies on black-box adversarial attacks have become increasingly pr...

Black-Box Saliency Map Generation Using Bayesian Optimisation

Saliency maps are often used in computer vision to provide intuitive int...

PPCR: Learning Pyramid Pixel Context Recalibration Module for Medical Image Classification

Spatial attention mechanism has been widely incorporated into deep convo...

Towards black-box parameter estimation

Deep learning algorithms have recently shown to be a successful tool in ...

Code Repositories


Source code for our WACV 2020 paper ``Iterative and Adaptive Sampling with Spatial Attention for Black-Box Model Explanations"

view repo

Please sign up or login with your details

Forgot password? Click here to reset