In this section we provide a more detailed derivation of the proposed loss function (Equation 17). We make use of the fact that the negative entropy of the Dirichlet distribution is equivalent to the reverse KL-divergence to a flat Dirichlet, up to an additive constant which doesn't depend on the model. Additionally, we can see that by adding +1 to the target concentration parameters ˆ, we are now minimizing an upper bound to the KL-divergence between the mean and the ensemble. Then we divide through by ˆ 0 and drop the additive constant. This yields a loss which is remarkable similar to an ELBO.

Appendix The appendix is organized as follows. We also provide details of the annotation/calibration process and the baseline neural networks (NNs) in Section D and E, respectively. We discuss results regarding each weather condition and consideration of the K-Radar dataset as a pre-training dataset for other Radar tensor datasets in Section F and G, respectively. Finally, we introduce details of devkits and list relevant URLs to help with understanding the content of the paper in Section H and I, respectively. A.1 Additional samples of the K-Radar dataset and explanation of LPCs for each weather condition In the sleet (Figure 8-(e)) or heavy snow (Figure 8-(g)) condition, the Lidar point cloud (LPC) measurements of some objects ahead are lost when the ego-vehicle is driving.

Unmanned Aerial V ehicles (UA Vs), equipped with cameras, are employed in numerous applications, including aerial photography, surveillance, and agriculture. In these applications, robust object detection and tracking are essential for the effective deployment of UA Vs.

In the simulation, we consider that the UAV swarm is flying over diverse simulated scenes at various altitudes. Each UAV has a sensing device to collect RGB images, a computation device to perceive the environment with a perception model, and a communication 9 device to transmit perception information among UAVs. In this setting, the UAV swarm is able to achieve 2D/3D object detection, pixel-wise or bird's-eye-view (BEV) semantic segmentation in a collaborative manner.