(ACSF ST-Encoder), the Asymptotic Cross-scale Feature-fusion Module (ACCFM) is designed to address the issue of information degradation caused by the propagation of high-level semantic information, thereby extracting high-quality multi-scale features to provide superior features for subsequent spatio-...
First, a cross-scale feature fusion module is devised to improve the detection performance of multiscale and partially occluded objects. This module fuses the global features of different residual layers and multiscale local region features, thereby improving the multiscale feature fusion capability of...
Multi-scale Feature Fusion Group 为获得精确的边缘信息,我们构建了CCB模块,见上图。除了Cross卷积外,CCB还包含F-Norm与CA(通道注意力,没什么可说的),两者分别用于空域与通道信息重要性挖掘。F-Norm可表示如下:F(i)out=(F(i)in⊗k(i)+b(i))+F(i)in 更多关于F-Norm的介绍可参考《Iterative Network fo...
Second, the bidirectional crossing (BiC) module is embedded to construct a bidirectional cross-scale feature fusion network (BiCCFM), which provides more accurate localization clues to enhance the feature representation on small targets. Finally, combined with non-stridden convolution, the SPD-Conv ...
Feature fusion 在获得每一层的特征映射后,我们构建了一个两阶段的特征融合模块(feature Fusion Module, FFM)来增强信息交互,并将两种模式的特征合并成一个单一的特征映射。如上图所示,在阶段1,两个分支仍然保持,并设计了交叉注意机制,在两个分支之间进行全局信息交换。然后,将这两个分支的输出连接起来。在第二阶段...
Multi-scale Feature Fusion Group 为获得精确的边缘信息,我们构建了CCB模块,见上图。除了Cross卷积外,CCB还包含F-Norm与CA(通道注意力,没什么可说的),两者分别用于空域与通道信息重要性挖掘。F-Norm可表示如下: 更多关于F-Norm的介绍可参考《Iterative Network for Image Super-resolution》一文,为方便理解,笔者在...
Specifically, in the feature encoding part, we adopt a two-stream Swin Transformer encoder to extract multi-level and multi-scale features from RGB images and depth images respectively to model global information. In the feature fusion part, we design a cross-modal attention fusion module, which...
To solve these problems, we propose a simple but effective cross-scale fusion method that fully uses the information of multi-scale feature maps. In addition, to better utilize the multi-scale contextual information, we designed the Selective Information Enhancement (SIE) module. The SIE ...
To address the above problems, we designed an end-to-end Lightweight Cross-scale Feature Fusion Network named LCFFNet, which achieved better performance with lower parameters. The LCFFNet model consists of three parts: Lightweight HRNet-like (LHRNet), Cross-Resolution-Aware Semantics Module (CRA...
Finally, we utilize the Feature Pyramid Aggregation Network for multi-scale feature fusion, achieving a deeper integration of the complementary data. Extensive experiments show that the proposed approach achieves competitive performances on MP6D, LM, and LM-O datasets....