In this paper, we proposed a "Multi-Level Attention Network" (MLAN), which defines a multi-level structure, including layer, block, and group levels to get hierarchical attention and combines corresponding residual information for better feature extraction. We also constructed a shared mask attention module (SMA) which can significantly reduce the number of parameters compared with conventional attention methods. Based on the MLAN and SMA, we further investigated a variety of information fusion modules for better feature fusion at different levels. We conducted classification task experiments based on the ResNet backbone with different depths, and the experimental results show that our method has a significant performance improvement over the backbone on CIFAR10 and CIFAR100 datasets. Meanwhile, compared with the mainstream attention methods, our MLAN performs better with higher accuracy as well as less parameters and computation complexity. We also visualized some intermediate feature maps and explained why our MLAN performs well.INDEX TERMS multi-level structure; shared mask attention; hierarchical attention aggregation; information fusion.

Interrupted sampling repeater jamming (ISRJ) is becoming more widely used in electronic countermeasures (ECM), thanks to the development of digital radio frequency memory (DRFM). Radar electronic counter-countermeasure (ECCM) is much more difficult when the jamming signal is coherent with the emitted signal. Due to the intermittent transmission feature of ISRJ, the energy accumulation of jamming on the matched filter shows a ‘ladder’ characteristic, whereas the real target signal is continuous. As a consequence, the time delay and distribution of the jamming slice can be obtained based on searching the truncated-matched-filter (TMF) matrix. That is composed of pulse compression (PC) results under matched filters with different lengths. Based on the above theory, this paper proposes a truncated matched filter method by the reconstruction of jamming slices to suppress ISRJ of linear frequency modulation (LFM) radars. The numerical simulations indicate the effectiveness of the proposed method and validate the theoretical analysis.

No abstract

No abstract

No abstract