Increasing demands for understanding the internal behaviors of convolutional neural networks (CNNs) have led to remarkable improvements in explanation methods. Particularly, several class activation mapping (CAM) based methods, which generate visual explanation maps by a linear combination of activation maps from CNNs, have been proposed. However, the majority of the methods lack a theoretical basis in how to assign their weighted linear coefficients. In this paper, we revisit the intrinsic linearity of CAM w.r.t. the activation maps. Focusing on the linearity, we construct an explanation model as a linear function of binary variables which denote the existence of the corresponding activation maps. With this approach, the explanation model can be determined by the class of additive feature attribution methods which adopts SHAP values as a unified measure of feature importance. We then demonstrate the efficacy of the SHAP values as the weight coefficients for CAM. However, the exact SHAP values are incalculable. Hence, we introduce an efficient approximation method, referred to as LIFT-CAM. On the basis of DeepLIFT, our proposed method can estimate the true SHAP values quickly and accurately. Furthermore, it achieves better performances than the other previous CAM-based methods in qualitative and quantitative aspects.
For RFID-based applications, the uniqueness of ID assigned to each RFID tag should be guaranteed. Several research/standard organizations such as EPCglobal, ISO/IEC, Ubiquitous ID Center, and so on, have developed their own Unique Item ID (UII) specifications. The existence of various UII schemes may cause interoperability problems between applications using different UII schemes when those applications are operated on future global Internet network environment. In addition, it is expected that the traffic for UII query will be increased ten-times higher than that for DNS query in the current Internet. In order to overcome these problems, this paper proposes a fast tree-based classification algorithm applicable for various UII schemes, which can make it efficient to construct global directory lookup services for RFID applications with various UII schemes. Since the proposed scheme can be operated on readers, it can not only distribute traffic loads for UII queries, but also global RFID networks.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.