Cluster-CAM: Cluster-weighted visual interpretation of CNNs' decision in image classification.

Despite the tremendous success of convolutional neural networks (CNNs) in computer vision, the mechanism of CNNs still lacks clear interpretation. Currently, class activation mapping (CAM), a famous visualization technique to interpret CNN's decision, has drawn increasing attention. Gradient-based CAMs are efficient, while the performance is heavily affected by gradient vanishing and exploding. In contrast, gradient-free CAMs can avoid computing gradients to produce more understandable results. However, they are quite time-consuming because hundreds of forward interference per image are required. In this paper, we proposed Cluster-CAM, an effective and efficient gradient-free CNN interpretation algorithm. Cluster-CAM can significantly reduce the times of forward propagation by splitting the feature maps into clusters. Furthermore, we propose an artful strategy to forge a cognition-base map and cognition-scissors from clustered feature maps. The final salience heatmap will be produced by merging the above cognition maps. Qualitative results conspicuously show that Cluster-CAM can produce heatmaps where the highlighted regions match the human's cognition more precisely than existing CAMs. The quantitative evaluation further demonstrates the superiority of Cluster-CAM in both effectiveness and efficiency.

The Deep-Match Framework: R-Peak Detection in Ear-ECG.

The Ear-ECG provides a continuous Lead I like electrocardiogram (ECG) by measuring the potential difference related to heart activity by electrodes which are embedded within earphones. However, the significant increase in wearability and comfort enabled by Ear-ECG is often accompanied by a degradation in signal quality - an obstacle that is shared by the majority of wearable technologies. We aim to resolve this issue by introducing a Deep Matched Filter (Deep-MF) for the highly accurate detection of R-peaks in wearable ECG, thus enhancing the utility of Ear-ECG in real-world scenarios. The Deep-MF consists of an encoder stage, partially initialised with an ECG template, and an R-peak classifier stage. Through its operation as a Matched Filter, the encoder searches for matches with an ECG template in the input signal, prior to filtering these matches with the subsequent convolutional layers and selecting peaks corresponding to the ground-truth ECG. The latent representation of R-peak information is then fed into a R-peak classifier, of which the output provides precise R-peak locations. The proposed Deep Matched Filter is evaluated using leave-one-subject-out cross-validation over 36 subjects with an age range of 18-75, with the Deep-MF outperforming existing algorithms for R-peak detection in noisy ECG. The Deep-MF achieves a median R-peak recall of 94.9% and a median precision of 91.2% across subjects when evaluated with leave-one-subject-out cross validation. Overall, this Deep-Match framework serves as a valuable step forward for the real-world functionality of Ear-ECG and, through its interpretable operation, the acceptance of deep learning models in e-Health.

Analytical interpretation of the gap of CNN's cognition between SAR and optical target recognition.

Synthetic aperture radar (SAR) automatic target recognition (ATR) is a crucial technique utilized in various scenarios of geoscience and remote sensing. Despite the remarkable success of convolutional neural networks (CNNs) in optical vision tasks, the application of CNNs in SAR ATR is still a challenging area due to the significant differences in the imaging mechanisms of SAR and optical images. This paper analytically addresses the cognitive gap of CNNs between optical and SAR images by leveraging multi-order interactions to measure their representation capacity. Furthermore, we propose a subjective evaluation strategy to compare human interactions with those of CNNs. Our findings reveal that CNNs operate differently for optical and SAR images. Specifically, for SAR images, CNNs' representation capacity is comparable to that of humans, as they can encode intermediate interactions better than simple and complex ones. In contrast, for optical images, CNNs excel at encoding simple and complex interactions, but not intermediate interactions.

A class of doubly stochastic shift operators for random graph signals and their boundedness.

A class of doubly stochastic graph shift operators (GSO) is proposed, which is shown to exhibit: (i) lower and upper L2-boundedness for locally stationary random graph signals, (ii) L2-isometry for i.i.d. random graph signals with the asymptotic increase in the incoming neighbourhood size of vertices, and (iii) preservation of the mean of any graph signal - all prerequisites for reliable graph neural networks. These properties are obtained through a statistical consistency analysis of the proposed graph shift operator, and by exploiting the dual role of the doubly stochastic GSO as a Markov (diffusion) matrix and as an unbiased expectation operator. For generality, we consider directed graphs which exhibit asymmetric connectivity matrices. The proposed approach is validated through an example on the estimation of a vector field.

Nonparametric algorithm for local frequency estimation of multidimensional signals.

Local frequency (LF) estimation of multidimensional (md) signals is considered. The md-Wigner distribution (WD) is used as the LF estimator. The LF is estimated based on the positions of the WD maxima. A nonparametric algorithm for the LF estimation is developed. It is based on the intersection of confidence intervals rule. This algorithm produces an adaptive window size in the WD which gives almost minimal mean squared error of the estimate. A simplified version of this algorithm is developed, with the starting estimate being produced with the WD of one-dimensional signals. Theory is illustrated in examples.