Our method builds upon the Open-Det (OD) framework, introducing two new elements to the loss function. These elements enhance the known embedding space's clustering and expand the unknown space's low-density regions. The first addition is the Class Wasserstein Anchor (CWA), a new function ...
Bottou. Wasserstein gener- ative adversarial networks. In Proc. of International Confer- ence on Machine Learning, pages 214–223, August 2017. [3] A. Arsalan Soltani, H. Huang, J. Wu, T. D. Kulkarni, and J. B. Tenenbaum. Synthesizing 3D shapes via modeling...