Unsupervised Object Representation Learning using Translation and Rotation Group Equivariant V AE (Supplementary Material)

A.1 Calculating Kullback-Leibler divergence Based on the standard definition for the KL-divergence, we have: KL ( q (z, θ, t, r| y)||p( z, θ, t, r)) = null We generated two datasets of MNIST(N) and MNIST(U), by rotating and translating digits in MNIST. Images in both of the datasets are 50x50 pixels. A.3 Digit-wise rotation correlation, and RMSE of the predicted rotations We created a new dataset using multiple rotated and translated digits from MNIST(U). Some predicted rotations for digits 0, 1, and 8 are off by π from their ground-truth values. We find that the model correctly identifies and reconstructs the objects (Figure 3).