Ramesh Raskar

Designing Neural Network Architectures using Reinforcement Learning

2016 · arXiv (Cornell University)

At present, designing convolutional neural network (CNN) architectures requires both human expertise and labor. New architectures are handcrafted by careful experimentation or modified from a handful of existing networks. We introduce MetaQNN, a meta-modeling algorithm …

Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest

2019 · arXiv (Cornell University)

In this paper we investigate the usage of adversarial perturbations for the purpose of privacy from human perception and model (machine) based detection. We employ adversarial perturbations for obfuscating certain variables in raw data while …

Decouple-and-Sample: Protecting sensitive information in task agnostic data release

2022 · arXiv (Cornell University)

We propose sanitizer, a framework for secure and task-agnostic data release. While releasing datasets continues to make a big impact in various applications of computer vision, its impact is mostly realized when data sharing is …