Convolutional neural networks (CNNs) have been widely used in a range of tasks because of its robust convolutional feature transformation ability. In this paper, we propose a novel type of convolution called Boosting Attention Convolution (BAC) to improve the basic convolutional feature transformation process of CNNs. The proposed method is designed based on two principles, boosting and attention mechanism. Specifically, we design a set of simple yet effective Boosting Attention Modules (BAM) within grouped convolution, which progressively recalibrate distribution of feature map and enable the future filters nested in a convolution layer to focus more on the feature regions that are unactivated by previous filters. Thus, it can help CNNs generate more discriminative representations by explicitly incorporating richer information. The experimental results on various datasets verify that BAC outperforms state-of-the-art methods. More importantly, the proposed BAC is a general convolution that can be deployed to various modern networks without introducing much parameters and computational complexity.

Traditionally, the channelization structures of wireless technologies (802.11/ZigBee/BLE) have been fixed. Each node content for the spectrum is assigned one channel with a specific bandwidth. However, classical channel‐based spectrum sensing and sharing algorithms have great limitations to further optimize spectrum utilization when multiple IoT with different wireless technologies coexisting in the same environment. Therefore, exploring the fine‐grained spectrum sensing algorithm becomes an essential work to further improve the spectrum utilization efficiency, especially in the Industrial Scientific Medical (ISM) band. This paper proposes Subcarrier-Sniffer, a novel subcarrier‐level spectrum sensing and sharing method, which utilizes channel state information (CSI) to sense the fine‐grained status of each subcarrier of the traditional channel. To evaluate the performance of Subcarrier-Sniffer, we implemented Subcarrier-Sniffer by USRP B200min, and the experimental results show that the accuracy of subcarrier‐level spectrum sensing could achieve 100% in our settings that the distance between Subcarrier-Sniffer and the monitor is not greater than 7 m. Subcarrier-Sniffer could be applied in WiFi and ZigBee, WiFi and BLE, and WiFi and LTE‐U coexisted environments for better spectrum utilization.