I work on the IARPA BRIAR project with a team that includes academic and industry partners.
In initial work , we looked at the effect atmospherics on deep learning models. Ongoing work is looking at algorithms to learn feature representations invariant to optical atmospheric turbulence.
- Robbins, W., & Boult, T. E. (2022). On the Effect of Atmospheric Turbulence in the Feature Space of Deep Face Recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 1618-1626).