JPEG Domain Residual Networks
In this work we develop the popular Residual Network architecture in the JPEG domain. Our goal
is to produce a formulation which gives a result that is as possible to the spatial domain network,
but which can operate on compressed JPEG images. Our formulation is generic and has applicability
outside of classification objective that we show as an example. We show a notable performance increase
by processing in the JPEG domain. This work was funded by Facebook Inc. and published in the
proceedings of the International Conference on Computer Vision 2019.
The CORE3D program aims to develop technology that generates, in an
automated way, accurate 3D object models with real physical properties, from multiple
data sources including commercial satellite panchromatic and multi-spectral imagery for
global coverage, and airborne imagery and Geographic Information System (GIS) vector
data, where available, for improved resolution and fidelity.
DARPA's Squad X Core Technologies (SXCT) program aims to develop novel technologies that could be
integrated into user-friendly systems that would extend squad awareness and engagement capabilities
without imposing physical and cognitive burdens. The goal is to speed the development of new, lightweight,
integrated systems that provide infantry squads unprecedented awareness, adaptability and flexibility in
complex environments, and enable dismounted Soldiers and Marines to more intuitively understand and
control their complex mission environments.
View my profile on Google Scholar
Amer, Mohamed R., Timothy J. Shields, Amir Tamrakar, Max Ehlrich, and Timur Almaev. "Deep multi-task representation learning." U.S. Patent Application 16/085,859, filed January 31, 2019.
Ehrlich, Max, and Larry Davis. "Deep Residual Learning in the JPEG Transform Domain." arXiv preprint arXiv:1812.11690. 2018.
Ghosh, Arthita, Max Ehrlich, Sohil Shah, Larry Davis, and Rama Chellappa. "Stacked U-Nets for Ground Material Segmentation in Remote Sensing Imagery." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 257-261. 2018.
Shields, Timothy J., Mohamed R. Amer, Max Ehrlich, Amir Tamrakar. "Action-Affect-Gender Classification using Multi-Task Representation Learning." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 2249-2258. 2017.
Ehrlich, Max, Timothy J. Shields, Timur Almaev, and Mohamed R. Amer. "Facial attributes classification using multi-task representation learning." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 47-55. 2016.
Ehrlich, Max, and Philippos Mordohai. "Discriminative hand localization in depth images." In Proceedings of the IEEE Symposium on 3D User Interfaces, pp. 239-240. 2016.
Ehrlich, Max. "Discriminative Hand Tracking from Depth Images." Master's Thesis, Stevens Institute of Technology. 2015
I currently maintain a patch and automatic .deb build system for the
Linux kernel with ACS Override capability.
If you need to bypass IOMMU groups for whatever reason and you don't have native ACS (and you use Ubuntu Linux),
then you might be interested in my packages.
Find more of my open source projects on Gitlab or