Multiresolution generative adversarial networks with bidirectional adaptive-stage progressive guided fusion for remote sensing image

Remote sensing image(RSI)with concurrently high spatial,temporal,and spectral resolutions cannot be produced by a single sensor.Multisource RSI fusion is a convenient technique to realize high spatial resolution multispectral(MS)images(spatial spectral fusion,i.e.SSF)and high temporal and spatial resolution MS images(spatiotemporal fusion,i.e.STF).Currently,deep learning-based fusion models can only implement SSF or STF,lacking models that perform both SSF and STF.Multiresolution generative adversarial networks with bidirectional adaptive-stage progressive guided fusion(BAPGF)for RSI are proposed to implement both SSF and STF,namely BPF-MGAN.A bidirectional adaptive-stage feature extraction architecture infine-scale-to-coarse-scale and coarse-scale-to-fine-scale modes is introduced.The designed BAPGF introduces a previous fusion result-oriented cross-stage-level dual-residual attention fusion strategy to enhance critical information and suppress superfluous information.Adaptive resolution U-shaped discriminators are implemented to feed multiresolution context into the generator.A generalized multitask loss function unlimited by no-reference images is developed to strengthen the model via constraints on the multiscale feature,structural,and content similarities.The BPF-MGAN model is validated on SSF datasets and STF datasets.Compared with the state-of-the-art SSF and STF models,results demonstrate the superior performance of the proposed BPF-MGAN model in both subjective and objective evaluations.

AM-PSPNet:Pyramid Scene Parsing Network Based on Attentional Mechanism for Image Semantic Segmentation

In this paper,AM-PSPNet is proposed for image semantic segmentation.AM-PSPNet embeds the efficient channel attention(ECA)module in the feature extraction stage of the convolutional network and makes the network pay more attention to the channels with obvious classification characteristics through end-to-end learning.To recognize the edges of objects and small objects more effectively,AM-PSPNet proposes a deep guidance fusion(DGF)module to generate global contextual attention maps to guide the expression of shallow information.The average crossover ratio of the proposed algorithm on the Pascal VOC 2012 dataset and Cityscapes dataset reaches 78.8%and 69.1%,respectively.Comparedwith the other four network models,the accuracy and average crossover ratio of AM-PSPNet are improved.