Hierarchical Dynamic Masks for Visual Explanation of Neural Networks

01/12/2023
by   Yitao Peng, et al.
0

Saliency methods generating visual explanatory maps representing the importance of image pixels for model classification is a popular technique for explaining neural network decisions. Hierarchical dynamic masks (HDM), a novel explanatory maps generation method, is proposed in this paper to enhance the granularity and comprehensiveness of saliency maps. First, we suggest the dynamic masks (DM), which enables multiple small-sized benchmark mask vectors to roughly learn the critical information in the image through an optimization method. Then the benchmark mask vectors guide the learning of large-sized auxiliary mask vectors so that their superimposed mask can accurately learn fine-grained pixel importance information and reduce the sensitivity to adversarial perturbations. In addition, we construct the HDM by concatenating DM modules. These DM modules are used to find and fuse the regions of interest in the remaining neural network classification decisions in the mask image in a learning-based way. Since HDM forces DM to perform importance analysis in different areas, it makes the fused saliency map more comprehensive. The proposed method outperformed previous approaches significantly in terms of recognition and localization capabilities when tested on natural and medical datasets.

READ FULL TEXT

page 5

page 8

page 9

page 14

research
07/17/2022

MDM:Visual Explanations for Neural Networks via Multiple Dynamic Mask

The active region lookup of a neural network tells us which regions the ...
research
10/19/2020

Investigating and Simplifying Masking-based Saliency Methods for Model Interpretability

Saliency maps that identify the most informative regions of an image for...
research
10/01/2019

Underwhelming Generalization Improvements From Controlling Feature Attribution

Overfitting is a common issue in machine learning, which can arise when ...
research
12/04/2022

CoupAlign: Coupling Word-Pixel with Sentence-Mask Alignments for Referring Image Segmentation

Referring image segmentation aims at localizing all pixels of the visual...
research
08/07/2022

Shap-CAM: Visual Explanations for Convolutional Neural Networks based on Shapley Value

Explaining deep convolutional neural networks has been recently drawing ...
research
03/25/2021

Group-CAM: Group Score-Weighted Visual Explanations for Deep Convolutional Networks

In this paper, we propose an efficient saliency map generation method, c...
research
06/29/2020

Scaling Symbolic Methods using Gradients for Neural Model Explanation

Symbolic techniques based on Satisfiability Modulo Theory (SMT) solvers ...

Please sign up or login with your details

Forgot password? Click here to reset