Measuring and improving the quality of visual explanations

The ability of to explain neural network decisions goes hand in hand with their safe deployment. Several methods have been proposed to highlight features important for a given network decision. However, there is no consensus on how to measure effectiveness of these methods. We propose a new procedure for evaluating explanations. We use it to investigate visual explanations extracted from a range of possible sources in a neural network. We quantify the benefit of combining these sources and challenge a recent appeal for taking bias parameters into account. We support our conclusions with a general assessment of the impact of bias parameters in ImageNet classifiers

READ FULL TEXT

page 1

page 2

page 8

page 10

page 11

page 12

page 13

page 15

research
09/19/2019

Highlighting Bias with Explainable Neural-Symbolic Visual Reasoning

Many high-performance models suffer from a lack of interpretability. The...
research
06/29/2021

On the Interaction of Belief Bias and Explanations

A myriad of explainability methods have been proposed in recent years, b...
research
05/16/2022

Sparse Visual Counterfactual Explanations in Image Space

Visual counterfactual explanations (VCEs) in image space are an importan...
research
11/09/2022

On the Robustness of Explanations of Deep Neural Network Models: A Survey

Explainability has been widely stated as a cornerstone of the responsibl...
research
12/10/2020

Debiased-CAM for bias-agnostic faithful visual explanations of deep convolutional networks

Class activation maps (CAMs) explain convolutional neural network predic...
research
07/16/2020

The role of collider bias in understanding statistics on racially biased policing

Contradictory conclusions have been made about whether unarmed blacks ar...
research
10/07/2022

Quantitative Metrics for Evaluating Explanations of Video DeepFake Detectors

The proliferation of DeepFake technology is a rising challenge in today'...

Please sign up or login with your details

Forgot password? Click here to reset