VITA

IDG Connect: "Reducing energy use in neural networks", Jan 2021
MIT News: "Shrinking massive neural networks used to model language", Dec 2020
US Army Research Lab selected our work as No. 3 in US ARL’s “10 Coolest Techniques” of the year [Video Demo], Oct 2020
Tech Xplore: "Fooling deep neural networks for object detection with adversarial 3-D logos", Jul 2020
Synced AI Technology & Industry Review: "AutoML + GAN = AutoGAN! AI can now design better GAN models than humans", Aug 2019
Adobe Research Blog: "Smart home? Adversarial machine learning could protect your privacy", Nov 2018

IEEE TPAMI'20 + ECCV'18, Privacy attributes in HMDB51 (PA-HMDB51) dataset [Webpage]
IJCV'20 + CVPR'19, Multi-Purpose Image Deraining (MPID) dataset. [Webpage]
IEEE TIP'19, REalistic Single Image DEhazing (RESIDE) dataset. [Webpage]
ACM MM'15, Adobe Visual Font Recognition (VFR) dataset. [Webpage]

At UT Austin

At TAMU

Our three popular image enhancement algorithms: AOD-Net, EnlightenGAN, and DeblurGAN-V2, are included into the open-source GNU Image Manipulation Program toolbox (GIMP-ML), as deep-dehazing, enlighten, and deblur plugins.
DeepFont, an Adobe Photoshop built-in feature, as one of its leading contributors. [Official Photoshop Manual]
Distributed Machine Learning (DML) ToolBox, as part of Microsoft Prajna
Dehazing algorithms integrated in the Computer Vision Emergency Response (CVER) toolkit [by students Pritish Uplavikar and Ryan Wells] [Webpage]

Open Calls for Papers/Participation