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
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction
We present a randomized controlled trial for a model-in-the-loop regression task, with the goal of measuring the extent to which (1) good explanations of model predictions increase human accuracy, and (2) faulty explanat…
Decision MakingExperimental DesignREVEL Framework to measure Local Linear Explanations for black-box models: Deep Learning Image Classification case of study
Explainable artificial intelligence is proposed to provide explanations for reasoning performed by an Artificial Intelligence. There is no consensus on how to evaluate the quality of these explanations, since even the de…
DescriptiveExplainable artificial intelligenceimage-classificationImage ClassificationProbabilistic Super-Resolution of Solar Magnetograms: Generating Many Explanations and Measuring Uncertainties
Machine learning techniques have been successfully applied to super-resolution tasks on natural images where visually pleasing results are sufficient. However in many scientific domains this is not adequate and estimatio…
BIG-bench Machine LearningSuper-ResolutionInterpretation Quality Score for Measuring the Quality of interpretability methods
Machine learning (ML) models have been applied to a wide range of natural language processing (NLP) tasks in recent years. In addition to making accurate decisions, the necessity of understanding how models make their de…
GIFT: A Framework for Global Interpretable Faithful Textual Explanations of Vision Classifiers
Understanding deep models is crucial for deploying them in safety-critical applications. We introduce GIFT, a framework for deriving post-hoc, global, interpretable, and faithful textual explanations for vision classifie…
counterfactual