A dual attention-enhanced feature fusion module is proposed for multiscale decoder feature fusion to improve the mural segmentation effect. This module uses a cross-level aggregation strategy and an attention mechanism to weight the importance of different feature levels to obtain multilevel semantic ...
Multiscale feature fusion (MSFF) module Compared with the existing methods, we add a MSFF module to fuse the output of all the layers in the block after the last layer. Let xl be the output of the last layer in the block: $$x_{l} = H(x_{l - 1} ) \otimes H(x_{l - 2...
The mural segmentation model proposed in this paper adopts the methods of multiscale feature fusion and dual attention enhancement; its overall structure is shown in Fig.1. The model consists of three main parts: an improved CA_MobileViT feature extraction network, an attention-optimized residual a...
Fusion-attention mechanism From the first two modules, we obtain the global feature representation \(\:{Z}=[{{z}}_{1},{{z}}_{2},\ldots,{{z}}_{{n}}]\) embedded with dependency relations and the multi-level local feature representation \(\:{F}=[{{f}}_{1},{{f}}_{2},\l...
In this paper, we propose a novel multiscale feature fusion and enhancement network (MFFENet) for accurate parsing of RGBthermal urban road scenes even when the quality of the available RGB data is compromised. The proposed MFFENet consists of two encoders, a feature fusion layer, and a ...
In the coding layer, we designed a dual-channel separation and convolution module and then added residual connections to perform multiscale feature fusion on the input image and the feature map after dual-channel separation and convolution. By fusing features at different scales in the same coding...
Multiscale Feature Fusion Sampling(MFS): Inspired by EffificientDet (Tan et al., 2020), we modified the BiFPN module to make it suitable as a decoder. As shown in Fig. 5(c), we denoted the output of the features by the four stages in the encoder as X1_0, X2_0, X3_0 and X4...
First, this paper proposes amultiscale feature cascaded attention (MCFA) module, which extracts multiscale feature information throughmultiple continuous convolution paths, and uses doubleattention to realize multiscale feature information fusion of different paths. Second, the attention-gate mechanism is ...
Extracting useful features at multiple scales is a crucial task in computer vision. The emergence of deep-learning techniques and the advancements in convolutional neural networks (CNNs) have facilitated effective multiscale feature extraction that resul
Specifically, the multi-scale inter-layer guidance sub-network introduces three efficient fusion feature modules: the feature guided enhancement module, the feature learning module, and the feature cross-learning module. These modules are respectively used to extract the underlying feature information to ...