Commuting Conditional Gans For Multi-Modal Fusion
Siddharth Roheda, Hamid Krim, Benjamin S. Riggan
-
Members: FreeSPS
IEEE Members: $11.00
Non-members: $15.00Length: 14:58
04 May 2020
This paper presents a data driven approach to multi-modal fusion where a hidden latent sub-space between the different modalities is learned. The hidden space is estimated via a bank of Conditional GANs which also commute with each other, leading to an output that lies in a common subspace. Experimental results show improved detection performance compared to existing fusion techniques in ideal as well as noisy sensor condition.
