In section 1, we provide five alternatives to the FPN-like structure for fusing the dual-resolution feature maps of the feature backbone. The channels of all feature maps are aligned to 1024 by 1 1 conv layers. As shown in Figure 2, all five types of variants have similar overall performance. Additionally, we also compare type (a) and type (e) with their 256 channel counterparts in Figure 4. We can see that increasing number of channels does not affect the performance of type (e). This further justifies that type (a) is a more proper choice for DualRC-Net. 2 Figure 4: Comparison between 256 and 1024 output feature channels for type (a) and type (e).