Supplement for BIER

In this document we provide further insights into Boosting Independent Embeddings Robustly (BIER). First, in Section 2 we describe our method for loss functions operating on triplets. Next, in Section 3 we show how our method behaves when we vary the embedding size and the number of groups. In Section 4 we summarize the effect of our boosting based training approach and our initialization approach. We provide an experiment evaluating the impact of end-to-end training in Section 5. Further, in Section 6 we demonstrate that our method is applicable to generic image classification problems. Finally, we show a qualitative comparison of the different embeddings in our ensemble in Section 7 and some qualitative results in Section 8.