The concept bottleneck model (CBM), as a technique improving interpretability via linking pre- dictions to human-understandable concepts, makes high-risk and life-critical medical image classification ...

Abstract: In recent years, the advancement of sensor-based systems has increasingly relied on real-time heterogeneous data from multiple sources. Therefore research on data fusion has been a key to ...

Abstract: Post-hoc and inherently interpretable methods have shown great success in uncovering the inner workings of black-box models, whether by examining them after training or by explicitly ...