Convolutional neural networks have demonstrated efficacy in acquiring local features and spatial details; however, they struggle to obtain global information, which could potentially compromise the segmentation of important regions of an image. Transformer can increase the expressiveness of pixels by establishing global relationships between them. Moreover, some transformer-based self-attentive methods do not combine the advantages of convolution, which makes the model require more computational parameters. This work uses both Transformer and CNN structures to improve the relationship between image-level regions and global information to improve segmentation accuracy and performance in order to address these two issues and improve the semantic segmentation results at the same time. We first build a Feature Alignment Module (FAM) module to enhance spatial details and improve channel representations. Second, we compute the link between similar pixels using a Transformer structure, which enhances the pixel representation. Finally, we design a Pyramid Convolutional Pooling Module (PCPM) that both compresses and enriches the feature maps, as well as determines the global correlations among the pixels, to reduce the computational burden on the transformer. These three elements come together to form a transformer-based semantic segmentation feature fusion network (FFTNet). Our method yields 82.5% mIoU, according to experimental results based on the Cityscapes test dataset. Furthermore, we conducted various visualization tests using the Pascal VOC 2012 and Cityscapes datasets. The results show that our approach outperforms alternative approaches.

The ability to capture pixels' long-distance interdependence is beneficial to semantic segmentation. In addition, semantic segmentation requires the effective use of pixel-to-pixel similarity in the channel direction to enhance pixel regions. Asymmetric Non-local Neural Networks (ANNet) combine multi-scale spatial pyramidal pooling modules and Non-local blocks to reduce model parameters without sacrificing performance. However, ANNet does not consider pixel similarity in the channel direction in the feature map, so its segmentation effect is not ideal. This article proposes a Mutually Reinforcing Non-local Neural Networks (MRNNet) to improve ANNet. MRNNet consists specifically of the channel enhancement regions module (CERM), and the position-enhanced pixels module (PEPM). In contrast to Asymmetric Fusion Non-local Block (AFNB) in ANNet, CERM does not combine the feature maps of the high and low stages, but rather utilizes the auxiliary loss function of ANNet. Calculating the similarity between feature maps in channel direction improves the category representation of feature maps in the channel aspect and reduces matrix multiplication computation. PEPM enhances pixels in the spatial direction of the feature map by calculating the similarity between pixels in the spatial direction of the feature map. Experiments reveal that our segmentation accuracy for cityscapes test data reaches 81.9%. Compared to ANNet, the model's parameters are reduced by 11.35 (M). Given ten different pictures with a size of 2048 × 1024, the average reasoning time of MRNNet is 0.103(s) faster than that of the ANNet model.

The wave-packet dynamical approach was used to investigate the excited-state intramolecular proton transfer (PT) of 5′-amino-2-(2′-hydroxyphenyl) benzimidazole (P1) based on the relaxed potential surfaces. For the involved PT process of P1 molecule, the quantum chemical calculation shows that relative to the ground state S0 with a single potential well, the excited state S1 with a double potential well can give much dynamical information. It is also found that because of the existence of a shallow potential barrier on the excited state S1, the PT in it is much easier than that in the ground state S0. When a laser field is used to pump the wave packet and induce the PT process, the external field parameters, such as the frequency and the envelope, also have influences on the PT process because of the impact of both pump time and the energy gap between two states. This kind of external field effect on the PT process gives a specific perspective to examine its dynamical mechanism and provides a reference for exploring the light-induced biophysical processes.