Investigating Bias in Image Classification using Model Explanations
We evaluated whether model explanations could efficiently detect bias in image classification by highlighting discriminating features, thereby removing the reliance on sensitive attributes for fairness calculations. To this end, we formulated important characteristics for bias detection and observed how explanations change as the degree of bias in models change. The paper identifies strengths and best practices for detecting bias using explanations, as well as three main weaknesses: explanations poorly estimate the degree of bias, could potentially introduce additional bias into the analysis, and are sometimes inefficient in terms of human effort involved.
Code (0)
등록된 구현이 없습니다.
Tasks
Bias DetectionClassificationFairnessGeneral Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
DiG-IN: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations
While deep learning has led to huge progress in complex image classification tasks like ImageNet unexpected failure modes e.g. via spurious features call into question how reliably these classifiers work in the wild.…
counterfactualimage-classificationImage ClassificationImage GenerationDiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations
While deep learning has led to huge progress in complex image classification tasks like ImageNet, unexpected failure modes, e.g. via spurious features, call into question how reliably these classifiers work in the wild. …
counterfactualimage-classificationImage ClassificationImage GenerationCan AI Explanations Make You Change Your Mind?
In the context of AI-based decision support systems, explanations can help users to judge when to trust the AI's suggestion, and when to question it. In this way, human oversight can prevent AI errors and biased decision…
Investigating and Explaining the Frequency Bias in Image Classification
CNNs exhibit many behaviors different from humans, one of which is the capability of employing high-frequency components. This paper discusses the frequency bias phenomenon in image classification tasks: the high-frequen…
Classificationimage-classificationImage ClassificationConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases
ConvNets and Imagenet have driven the recent success of deep learning for image classification. However, the marked slowdown in performance improvement combined with the lack of robustness of neural networks to adversari…
image-classificationImage Classification