We propose a method for projecting images into the space of generative neural networks. We optimize for transformation to counteract the model biases in a generative neural networks. To alleivate optimization difficulties, we propose the use of hybrid (gradient + ES) optimization.

Taking inspirations from feedback error control, we propose feedback adversarial learning (FAL) framework that can improve existing generative adversarial networks by leveraging spatial feedback from the discriminator into generative process.

We propose a learning algorithm for detecting visual image manipulations that is trained only using a large dataset of real photographs. The algorithm uses the automatically recorded photo EXIF metadata as supervisory signal for training a model to determine whether an image is self-consistent

We propose an end-to-end trainable framework that learns to exploit multiple viewpoints to synthesize a novel view without any 3D supervision. Our model consists of a flow prediction module and a pixel generation module to directly leverage information presented in source views as well as hallucinate missing pixels from statistical priors.

This work provides an empirical investigation into the various facets of this question, such as looking at the importance of the amount of examples, number of classes, balance between images-per-class and classes, and the role of fine and coarse grained recognition. We pre-train CNN features on various subsets of the ImageNet dataset and evaluate transfer performance on a variety of standard vision tasks.

We demonstrate that ultrasound can be used to define and steer the trajectory of light within scattering media by exploiting local pressure differences created by acoustic waves that result in refractive index contrasts.

We introduce a radical approach to use ultrasonic waves to confine and steer light deep (a few millimeters) into the tissue without having to insert a physical light guide. Ultrasonic pressure waves launched from outside can propagate in the brain tissue with minimal loss and change the density of medium locally and interact with light to define and steer the trajectory of light.

Here we present the first non-invasive methodology for optical delivery and steering deep inside the brain through creating reconfigurable light paths by ultrasonic waves via modulating the refractive and diffractive properties of the medium.