Skip to main content
. Author manuscript; available in PMC: 2025 Oct 3.
Published in final edited form as: IEEE Trans Vis Comput Graph. 2025 Oct;31(10):7436–7447. doi: 10.1109/TVCG.2025.3546644

Fig. 1.

Fig. 1.

AttributionScanner workflow involves three phases: Explainable Data Slice Finding, Slice Summarization and Annotation, and Slice Error Mitigation. The first phase: GradCAM is used to assist the generation of feature vectors and then obtain data slices. The second phase: users can identify and annotate slice error types such as core/spurious correlations and noisy labels with the help of Attribution Mosaic and Spuriousness propagation. The third phase: the annotation and user-verified Spuriousness are used on the ML side to mitigate slice errors.