Thermal Non-Line-of-Sight Imaging

2019Academic Paper
Tomohiro Maeda, Yiquin Wang, Ramesh Raskar, Achuta Kadambi
2019 IEEE International Conference on Computational Photography

We propose a novel non-line-of-sight (NLOS) imaging framework with long-wave infrared (IR). At long-wave IR wavelengths, certain physical parameters are more favorable for high-fidelity reconstruction. In contrast to prior work in visible light NLOS, at long-wave IR wavelengths, the hidden heat source acts as a light source. This simplifies the problem to a single bounce problem. In addition, surface reflectance has a much stronger specular reflection in the long-wave IR spectrum than in the visible light spectrum. We reformulate a light transport model that leverages these favorable physical properties of long-wave IR. Specifically, we demonstrate 2D shape recovery and 3D localization of a hidden object. Furthermore, we demonstrate near real-time and robust NLOS pose estimation of a human figure, the first such demonstration, to our knowledge.

Split Learning: A Resource Efficient Distributed Deep Learning Method without Sensitive Data Sharing

2019Presentation
Praneeth Vepakomma
Data Council San Francisco 2019

Reducing Leakage in Distributed Deep Learning for Sensitive Health Data

2019Academic Paper
Praneeth Vepakomma, Otkrist Gupta, Abhimanyu Dubey, Ramesh Raskar
ICLR 2019 AI for Social Good Workshop

For distributed machine learning with health data we demonstrate how minimizing distance correlation between raw data and intermediary representations (smashed data) reduces leakage of sensitive raw data patterns during client communications while maintaining model accuracy. Leakage (measured using KL Divergence between input and intermediate representation) is the risk associated with the invertibility from intermediary representations, can prevent resource poor health organizations from using distributed deep learning services. We demonstrate that our method reduces leakage in terms of distance correlation between raw data and communication payloads from an order of 0.95 to 0.19 and from 0.92 to 0.33 during training with image datasets while maintaining a similar classification accuracy.

On Unlimited Sampling and Reconstruction

2019Academic Paper
A Bhandari, F Krahmer, R Raskar
arXiv preprint arXiv: 1905.03901

Shannon’s sampling theorem is one of the cornerstone topics that is well understood and explored, both mathematically and algorithmically. That said, practical realization of this theorem still suffers from a severe bottleneck due to the fundamental assumption that the samples can span an arbitrary range of amplitudes. In practice, the theorem is realized using so-called analog-to-digital converters (ADCs) which clip or saturate whenever the signal amplitude exceeds the maximum recordable ADC voltage thus leading to a significant information loss. In this paper, we develop an alternative paradigm for sensing and recovery, called the Unlimited Sampling Framework. It is based on the observation that when a signal is mapped to an appropriate bounded interval via a modulo operation before entering the ADC, the saturation problem no longer exists, but one rather encounters a different type of information loss due to the modulo operation. Such an alternative setup can be implemented, for example, via so-called folding or self-reset ADCs, as they have been proposed in various contexts in the circuit design literature. The key task that we need to accomplish in order to cope with this new type of information loss is to recover a bandlimited signal from its modulo samples. In this paper we derive conditions when this is possible and present an empirically stable recovery algorithm with guaranteed perfect recovery. The sampling density required for recovery is independent of the maximum recordable ADC voltage and depends on the signal bandwidth only. Numerical experiments validate our approach and indeed show that it is possible to perfectly recover functions that take values that are orders of magnitude higher than the ADC’s threshold. Applications of the unlimited sampling paradigm can be found in a number of fields such as signal processing, communication and imaging.

Light-Field for RF

2019Academic Paper
Manikanta Kotaru, Guy Satat, Ramesh Raskar, Sachin Katti
arXiv:1901.03953

Most computer vision systems and computational photography systems are visible light based which is a small fraction of the electromagnetic (EM) spectrum. In recent years radio frequency (RF) hardware has become more widely available, for example, many cars are equipped with a RADAR, and almost every home has a WiFi device. In the context of imaging, RF spectrum holds many advantages compared to visible light systems. In particular, in this regime, EM energy effectively interacts in different ways with matter. This property allows for many novel applications such as privacy preserving computer vision and imaging through absorbing and scattering materials in visible light such as walls. Here, we expand many of the concepts in computational photography in visible light to RF cameras. The main limitation of imaging with RF is the large wavelength that limits the imaging resolution when compared to visible light. However, the output of RF cameras is usually processed by computer vision and perception algorithms which would benefit from multi-modal sensing of the environment, and from sensing in situations in which visible light systems fail. To bridge the gap between computational photography and RF imaging, we expand the concept of light-field to RF. This work paves the way to novel computational sensing systems with RF.

Distributed Private Machine Learning for Computer Vision: Federated Learning, Split Learning and Beyond

2019Presentation
Brendan McMahan, Jakub Konečný, Otkrist Gupta, Ramesh Raskar, Hassan Takabi, Praneeth Vepakomma
CVPR 2019 Tutorial

This tutorial presents different methods for protecting confidential data on clients while still allowing servers to train models. In particular, we focus on distributed deep learning approaches under the constraint that local data sources of clients (e.g. photos on phones or medical images at hospitals) are not allowed to be shared with the server or amongst other clients due to privacy, regulations or trust. We describe such methods that include federated learning, split learning, homomorphic encryption, and differential privacy for securely learning and inferring with neural networks. We also study their trade-offs with regards to computational resources and communication efficiency in addition to sharing practical know-how of deploying such systems.

Data Security and Privacy in the Age of Machine Learning

2019Presentation
Praneeth Vepakomma
Data Council San Francisco 2019

Data Markets to support AI for All: Pricing, Valuation and Governance

2019Academic Paper
Ramesh Raskar, Praneeth Vepakomma, Tristan Swedish, Aalekh Sharan
arXiv:1905.06462

We discuss a data market technique based on intrinsic (relevance and uniqueness) as well as extrinsic value (influenced by supply and demand) of data. For intrinsic value, we explain how to perform valuation of data in absolute terms (i.e just by itself), or relatively (i.e in comparison to multiple datasets) or in conditional terms (i.e valuating new data given currently existing data).

Split learning for health: Distributed deep learning without sharing raw patient data

2018
Praneeth Vepakomma, Otkrist Gupta, Tristan Swedish, Ramesh Raskar
arXiv:1812.00564

Can health entities collaboratively train deep learning models without sharing sensitive raw data? This paper proposes several configurations of a distributed deep learning method called SplitNN to facilitate such collaborations. SplitNN does not share raw data or model details with collaborating institutions. The proposed configurations of splitNN cater to practical settings of i) entities holding different modalities of patient data, ii) centralized and local health entities collaborating on multiple tasks and iii) learning without sharing labels. We compare performance and resource efficiency trade-offs of splitNN and other distributed deep learning methods like federated learning, large batch synchronous stochastic gradient descent and show highly encouraging results for splitNN.

No Peek: A Survey of private distributed deep learning

2018Academic Paper
Praneeth Vepakomma, Tristan Swedish, Ramesh Raskar, Otkrist Gupta, Abhimanyu Dubey
arXiv:1812.03288

We survey distributed deep learning models for training or inference without accessing raw data from clients. These methods aim to protect confidential patterns in data while still allowing servers to train models. The distributed deep learning methods of federated learning, split learning and large batch stochastic gradient descent are compared in addition to private and secure approaches of differential privacy, homomorphic encryption, oblivious transfer and garbled circuits in the context of neural networks. We study their benefits, limitations and trade-offs with regards to computational resources, data leakage and communication efficiency and also share our anticipated future trends.

Flash Photography for Data-Driven Hidden Scene Recovery

2018
Matthew Tancik, Guy Satat, Ramesh Raskar
arXiv:1810.11710

A Review of Homomorphic Encryption Libraries for Secure Computation

2018Academic Paper
Sai Sri Sathya, Praneeth Vepakomma, Ramesh Raskar, Ranjan Ramachandra and Santanu Bhattacharya
arXiv:1812.02428

In this paper we provide a survey of various libraries for homomorphic encryption. We describe key features and trade-offs that should be considered while choosing the right approach for secure computation. We then present a comparison of six commonly available Homomorphic Encryption libraries – SEAL, HElib, TFHE, Paillier, ELGamal and RSA across these identified features. Support for different languages and real-life applications are also elucidated.

3D Traffic Simulation for Autonomous Vehicles in Unity and Python

2018Academic Paper
Z Jin, T Swedish, R Raskar
arXiv preprint arXiv: 1810.12552

Over the recent years, there has been an explosion of studies on autonomous vehicles. Many collected large amount of data from human drivers. However, compared to the tedious data collection approach, building a virtual simulation of traffic makes the autonomous vehicle research more flexible, time-saving, and scalable. Our work features a 3D simulation that takes in real time position information parsed from street cameras. The simulation can easily switch between a global bird view of the traffic and a local perspective of a car. It can also filter out certain objects in its customized camera, creating various channels for objects of different categories. This provides alternative supervised or unsupervised ways to train deep neural networks. Another advantage of the 3D simulation is its conformation to physical laws. Its naturalness to accelerate and collide prepares the system for potential deep reinforcement learning needs.

Zensei: Embedded, Multi-electrode Bioimpedance Sensing for Implicit, Ubiquitous User Recognition

2017
Munehiko Sato, Rohan S Puri, Alex Olwal, Yosuke Ushigome, Lukas Franciszkiewicz, Deepak Chandra, Ivan Poupyrev, Ramesh Raskar
Proceeding CHI '17 Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems Pages 3972-3985

Training with Confusion for Fine-Grained Visual Classification

2017
Abhimanyu Dubey, Otkrist Gupta, Pei Guo, Ramesh Raskar, Ryan Farrell, Nikhil Naik
arXiv:1705.08016
1 2 3 13