X-BaD: A Flexible Tool for Explanation-Based Bias Detection

Pacini, Marco; Nesti, Federico; Biondi, Alessandro; Buttazzo, Giuseppe

doi:10.1109/csr51186.2021.9527956

Cited by 1 publication

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They used this as a justification to bridge global and local XAI (such as LRP, (Guided) Grad-CAM etc.). The previous work in [ 21 , 22 , 24 , 25 ] also belongs to this category. Here, we showed that this argument is not valid and global methods can be valid for bias discovery.…”

Section: Discussionmentioning

confidence: 99%

“…Some methods make use of clustering. Four extensions [ 21 , 22 , 23 , 24 ] of the spectral relevance analysis (SpRAy) framework [ 25 ] cluster layer-wise relevance propagation (LRP) heatmaps (synonymous: saliency maps, pixel attribution). The unsupervised discovery of bias in deep visual recognition models (UDIS) algorithm by Krishnakumar et al [ 26 ] clusters feature embeddings.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Validating Automatic Concept-Based Explanations for AI-Based Digital Histopathology

Sauter

Lodde

Nensa

et al. 2022

Sensors

View full text Add to dashboard Cite

Digital histopathology poses several challenges such as label noise, class imbalance, limited availability of labelled data, and several latent biases to deep learning, negatively influencing transparency, reproducibility, and classification performance. In particular, biases are well known to cause poor generalization. Proposed tools from explainable artificial intelligence (XAI), bias detection, and bias discovery suffer from technical challenges, complexity, unintuitive usage, inherent biases, or a semantic gap. A promising XAI method, not studied in the context of digital histopathology is automated concept-based explanation (ACE). It automatically extracts visual concepts from image data. Our objective is to evaluate ACE’s technical validity following design science principals and to compare it to Guided Gradient-weighted Class Activation Mapping (Grad-CAM), a conventional pixel-wise explanation method. To that extent, we created and studied five convolutional neural networks (CNNs) in four different skin cancer settings. Our results demonstrate that ACE is a valid tool for gaining insights into the decision process of histopathological CNNs that can go beyond explanations from the control method. ACE validly visualized a class sampling ratio bias, measurement bias, sampling bias, and class-correlated bias. Furthermore, the complementary use with Guided Grad-CAM offers several benefits. Finally, we propose practical solutions for several technical challenges. In contradiction to results from the literature, we noticed lower intuitiveness in some dermatopathology scenarios as compared to concept-based explanations on real-world images.

show abstract

Section: Discussionmentioning

confidence: 99%