Supplementary Material: Joint Learning of 2D-3D Weakly Supervised Semantic Segmentation Hyeokjun Kweon KAIST 0327june@kaist.ac.kr Kuk-Jin Y oon KAIST kjyoon@kaist.ac.kr 1 Implementation details

In the first phase, we individually train both 2D and 3D classifiers with the classification loss of each domain. After that, we jointly train them using the proposed 2D-to-3D and 3D-to-2D losses, in addition to the classification loss. Here, in the second phase, please note that we first train our framework without the 3D-to-2D loss for the first few epochs. As we explained in Section 4.1 of the main paper, we augment the images and point clouds before we In this subsection, we provide our augmentation methods in detail. On the other hand, when we use a smaller patch size, fine details of the image could not be preserved.