In the Adaptive Cross-Scale Fusion Spatio-Temporal Encoder (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...
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...
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 ...
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 ...
A cross-scale boost module with non-local network is firstly applied to enhance the ability of feature representation for OCT lesions with varying scales. To avoid lesion omission and misdetection, some positive-aware network designs are then added into a two-stage detection network, including ...
proposed (MPCFusion). To exploit deeper texture details, a feature extraction module based on convolution and vision Transformer is designed. With a view to correlating the shallow features between different modalities, a parallel cross-attention module is proposed, in which a parallel-channel model ...
The Cross Perceptron first captures the local correlations using multiple Multi-scale Cross Perceptron modules, facilitating the fusion of features across scales. The resulting multi-scale feature vectors are then spatially unfolded, concatenated, and fed through a Global Perceptron module to model ...
sion strategies: three simple heuristic approaches and the proposed cross-attention module as shown in Figure 3. Be- low we provide the details on these fusion schemes. 3.3. Multi-Scale Feature Fusion Let xi be the token sequence (both patch and CLS ...
(CRASM) and Adapt Feature Fusion Module (AFFM). Specifically, first, we designed a lightweight model named LHRNet. This model is obtained by replacing the second-stage and fourth-stage Basic blocks of HRNet with the DMSC-Basic block designed by us. The DMSC-Basic block is composed of ...
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....