The feature pyramid is a classic approach in object detection, and it can exploit multiscale feature information. In previous research, many object detection models that directly use image features extracted by
Based on the residual learning, we propose a multi-scale feature fusion residual block (MSFFRB) with multiple intertwined paths to adaptively detect and fuse image features at different scales. Furthermore, the outputs of each MSFFRB and the shallow features are used as the hierarchical features ...
为了解决上述问题,我们设计了一种多尺度扩张残差块(MDRB)fMDRB multi-scale dilated residual block (MDRB),它不仅可以有效地扩大感受野 receptive field 以感知帧之间的大像素运动, 还可以 在扩张卷积的帮助下可以很好地保留对象边界细节 捕获多尺度上下文信息。 具体的是: 首先堆叠两个 3 × 3 和 5 × 5 卷...
Residual learningMulti-scale feature fusionFractal networkRecent studies have shown that the use of deep convolutional neural networks (CNNs) can improve the performance of single image super-resolution reconstruction (SISR) methods. However, the existing CNN-based SISR model ignores the multi-scale ...
Multi-Scale Boosted Dehazing Network with Dense Feature Fusion笔记和代码本篇论文的主要创新点是 SOS增强策略和密集特征融合,创新点均是从其他领域进行挖掘。摘要提出了一种基于U-Net结构的具有密集特征融合…
Firstly, the fusion of global and local features is adopted to obtain more information of the vehicle and enhance the learning ability of the model; Secondly, the channel attention module in the feature extraction branch is embedded to extract the personalized features of the targeting vehicle; ...
One of the 3M layers contains a Multi-scale Spatial Feature Module (MSFM) and a Channel Mixing Module (CMM). Finally, we introduce global residual connectivity to learn the detail information and use a 1 × 1 convolution to adjust the channel information. Our network can be defined as, (1...
residual connections to extract high-dimensional feature information. The Position-wise Attention Block is used to capture the spatial dependencies of feature maps, and the Multi-scale Fusion Attention Block is to aggregate the channel dependencies between any feature maps via fusing High and Low-...
DWT block When the image information enters the block, it is decomposed into four subbands through DWT, and then it concats the four subbands. The resolution of the obtained feature information becomes half of the input, and the number of channels become 4 times, as a result the number of...
The SCAR block adds the channel attention (CA) and spatial attention (SA) mechanisms based on a double-layer convolution residual block. In addition, group convolution is introduced in the SCAR block to further reduce the parameters while preventing over-fitting. Moreover, a multi-scale feature ...