In recent years, advancements in remote-sensing image super-resolution have achieved remarkable performance. However, many methods demand significant computational resources. This is problematic for edge devices with limited computational capabilities. To alleviate this problem, we propose an attention-based multi-level feature fusion network (AMFFN) to enhance the resolution of remote-sensing images. This proposed network integrates three efficient design strategies to provide a lightweight solution. Initially, we design the partial shallow residual block (PSRB) to replace the redundant convolution operation. The PSRB optimizes feature extraction via partial convolution and capitalizes on information across channels using pointwise convolution. Subsequently, integrating the PSRB, our dynamic feature distillation block (DFDB) leverages an information distillation mechanism to distill and capture only the crucial features securing a robust feature depiction. Conclusively, for superior feature fusion, we conceptualized an attention-based multi-level feature fusion (AMFF) mechanism. The attention intrinsic to AMFF weighs the significance of features from varied branches, assuring that the resulting output is comprehensive and discerning. We conduct thorough experimental validation on two datasets of remote-sensing images and measure network complexity by evaluating network parameters and multi-adds operations. The results show that our method effectively balances computational complexity and performance. In addition, we have expanded the application of AMFFN to the field of natural image super-resolution. Experimental results on five benchmark test datasets further confirm the effectiveness of our method.

Considerable research and surveys indicate that skin lesions are an early symptom of skin cancer. Segmentation of skin lesions is still a hot research topic. Dermatological datasets in skin lesion segmentation tasks generated a large number of parameters when data augmented, limiting the application of smart assisted medicine in real life. Hence, this paper proposes an effective feedback attention network (FAC-Net). The network is equipped with the feedback fusion block (FFB) and the attention mechanism block (AMB), through the combination of these two modules, we can obtain richer and more specific feature mapping without data enhancement. Numerous experimental tests were given by us on public datasets (ISIC2018, ISBI2017, ISBI2016), and a good deal of metrics like the Jaccard index (JA) and Dice coefficient (DC) were used to evaluate the results of segmentation. On the ISIC2018 dataset, we obtained results for DC equal to 91.19% and JA equal to 83.99%, compared with the based network. The results of these two main metrics were improved by more than 1%. In addition, the metrics were also improved in the other two datasets. It can be demonstrated through experiments that without any enhancements of the datasets, our lightweight model can achieve better segmentation performance than most deep learning architectures.

The model, Transformer, is known to rely on a self-attention mechanism to model distant dependencies, which focuses on modeling the dependencies of the global elements. However, its sensitivity to the local details of the foreground information is not significant. Local detail features help to identify the blurred boundaries in medical images more accurately. In order to make up for the defects of Transformer and capture more abundant local information, this paper proposes an attention and MLP hybrid-encoder architecture combining the Efficient Attention Module (EAM) with a Dual-channel Shift MLP module (DS-MLP), called HEA-Net. Specifically, we effectively connect the convolution block with Transformer through EAM to enhance the foreground and suppress the invalid background information in medical images. Meanwhile, DS-MLP further enhances the foreground information via channel and spatial shift operations. Extensive experiments on public datasets confirm the excellent performance of our proposed HEA-Net. In particular, on the GlaS and MoNuSeg datasets, the Dice reached 90.56% and 80.80%, respectively, and the IoU reached 83.62% and 68.26%, respectively.