Exposing Image Classifier Shortcuts with Counterfactual Frequency (CoF) Tables
The rise of deep learning in image classification has brought unprecedented accuracy but also highlighted a key issue: the use of 'shortcuts' by models. Such shortcuts are easy-to-learn patterns from the training data that fail to generalise to new data. Examples include the use of a copyright watermark to recognise horses, snowy background to recognise huskies, or ink markings to detect malignant skin lesions. The explainable AI (XAI) community has suggested using instance-level explanations to detect shortcuts without external data, but this requires the examination of many explanations to confirm the presence of such shortcuts, making it a labour-intensive process. To address these challenges, we introduce Counterfactual Frequency (CoF) tables, a novel approach that aggregates instance-based explanations into global insights, and exposes shortcuts. The aggregation implies the need for some semantic concepts to be used in the explanations, which we solve by labelling the segments of an image. We demonstrate the utility of CoF tables across several datasets, revealing the shortcuts learned from them.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation
Shortcut learning is when a model -- e.g. a cardiac disease classifier -- exploits correlations between the target label and a spurious shortcut feature, e.g. a pacemaker, to predict the target label based on the shortcu…
counterfactualCounterfactual ExplanationImage GenerationDo ImageNet-trained models learn shortcuts? The impact of frequency shortcuts on generalization
Frequency shortcuts refer to specific frequency patterns that models heavily rely on for correct classification. Previous studies have shown that models trained on small image datasets often exploit such shortcuts, poten…
Counterfactual Generative Networks
Neural networks are prone to learning shortcuts -- they often model simple correlations, ignoring more complex ones that potentially generalize better. Prior works on image classification show that instead of learning a …
ClassificationcounterfactualGeneral ClassificationGPU+4DeCoDEx: Confounder Detector Guidance for Improved Diffusion-based Counterfactual Explanations
Deep learning classifiers are prone to latching onto dominant confounders present in a dataset rather than on the causal markers associated with the target class, leading to poor generalization and biased predictions. Al…
counterfactualImage GenerationWhat do neural networks learn in image classification? A frequency shortcut perspective
Frequency analysis is useful for understanding the mechanisms of representation learning in neural networks (NNs). Most research in this area focuses on the learning dynamics of NNs for regression tasks, while little for…
Data Augmentationimage-classificationImage ClassificationRepresentation Learning