2 papers
cs.LG2026
CB-SLICE: Concept-Based Interpretable Error Slice Discovery
Yael Konforti, Mateo Espinosa Zarlenga, Elaf Almahmoud +1
Despite strong average-case performance, deep learning models often exhibit systematic errors on specific population groups, known as error slices. Identifying these groups and the…
cs.CV2021
Inference Graphs for CNN Interpretation
Yael Konforti, Alon Shpigler, Boaz Lernerand Aharon Bar-Hillel
Convolutional neural networks (CNNs) have achieved superior accuracy in many visual related tasks. However, the inference process through intermediate layers is opaque, making it d…