Search Results for author:
Found 88 papers, 18 papers with code
Imaging Behind Occluders Using Two-Bounce Light
Hidden objects attenuate light that passes through the hidden space, leaving an observable signature that can be used to reconstruct their shape.
Towards Viewpoint Robustness in Bird's Eye View Segmentation
We introduce a technique for novel view synthesis and use it to transform collected data to the viewpoint of target rigs, allowing us to train BEV segmentation models for diverse target rigs without any additional data collection or labeling cost.
Conformal Prediction with Large Language Models for Multi-Choice Question Answering
In this work, we explore how conformal prediction can be used to provide uncertainty quantification in language models for the specific task of multiple-choice question-answering.
Federated Conformal Predictors for Distributed Uncertainty Quantification
Conformal prediction is emerging as a popular paradigm for providing rigorous uncertainty quantification in machine learning since it can be easily applied as a post-processing step to already trained models.
Domain Generalization In Robust Invariant Representation
Unsupervised approaches for learning representations invariant to common transformations are used quite often for object recognition.
Role of Transients in Two-Bounce Non-Line-of-Sight Imaging
Specifically, we study how ToF information can reduce the number of measurements and spatial resolution needed for shape reconstruction.
ORCa: Glossy Objects As Radiance-Field Cameras
By converting these objects into cameras, we can unlock exciting applications, including imaging beyond the camera's field-of-view and from seemingly impossible vantage points, e. g. from reflections on the human eye.
ORCa: Glossy Objects as Radiance Field Cameras
By converting these objects into cameras, we can unlock exciting applications, including imaging beyond the camera's field-of-view and from seemingly impossible vantage points, e. g. from reflections on the human eye.
Scalable Collaborative Learning via Representation Sharing
To do so, each client releases averaged last hidden layer activations of similar labels to a central server that only acts as a relay (i. e., is not involved in the training or aggregation of the models).
Differentially Private CutMix for Split Learning with Vision Transformer
Split learning (SL) detours this by communicating smashed data at a cut-layer, yet suffers from data privacy leakage and large communication costs caused by high similarity between ViT' s smashed data and input data.
Detection and Mapping of Specular Surfaces Using Multibounce Lidar Returns
We propose methods that use specular, multibounce lidar returns to detect and map specular surfaces that might be invisible to conventional lidar systems that rely on direct, single-scatter returns.
Fundamentals of Task-Agnostic Data Valuation
We capture these statistical differences through second moment by measuring diversity and relevance of the seller's data for the buyer; we estimate these measures through queries to the seller without requesting raw data.
Differentiable Agent-based Epidemiology
Mechanistic simulators are an indispensable tool for epidemiology to explore the behavior of complex, dynamic infections under varying conditions and navigate uncertain environments.
Private independence testing across two parties
We introduce $\pi$-test, a privacy-preserving algorithm for testing statistical independence between data distributed across multiple parties.
Visual Transformer Meets CutMix for Improved Accuracy, Communication Efficiency, and Data Privacy in Split Learning
Leveraging this, we develop a novel SL framework for ViT, coined CutMixSL, communicating CutSmashed data.
A Roadmap for Greater Public Use of Privacy-Sensitive Government Data: Workshop Report
Government agencies collect and manage a wide range of ever-growing datasets.
Physics vs. Learned Priors: Rethinking Camera and Algorithm Design for Task-Specific Imaging
Cameras were originally designed using physics-based heuristics to capture aesthetic images.
Physically Disentangled Representations
In this paper, we show the utility of inverse rendering in learning representations that yield improved accuracy on downstream clustering, linear classification, and segmentation tasks with the help of our novel Leave-One-Out, Cycle Contrastive loss (LOOCC), which improves disentanglement of scene parameters and robustness to out-of-distribution lighting and viewpoints.
Towards Learning Neural Representations from Shadows
We observe that shadows are a powerful cue that can constrain neural scene representations to learn SfS, and even outperform NeRF to reconstruct otherwise hidden geometry.
Learning to Censor by Noisy Sampling
The goal of this work is to protect sensitive information when learning from point clouds; by censoring the sensitive information before the point cloud is released for downstream tasks.
Decouple-and-Sample: Protecting sensitive information in 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 not inhibited by privacy concerns.
Server-Side Local Gradient Averaging and Learning Rate Acceleration for Scalable Split Learning
In recent years, there have been great advances in the field of decentralized learning with private data.
AdaSplit: Adaptive Trade-offs for Resource-constrained Distributed Deep Learning
In this work, we introduce AdaSplit which enables efficiently scaling SL to low resource scenarios by reducing bandwidth consumption and improving performance across heterogeneous clients.
Private measurement of nonlinear correlations between data hosted across multiple parties
We introduce a differentially private method to measure nonlinear correlations between sensitive data hosted across two entities.
DeepABM: Scalable, efficient and differentiable agent-based simulations via graph neural networks
We introduce DeepABM, a framework for agent-based modeling that leverages geometric message passing of graph neural networks for simulating action and interactions over large agent populations.
Sanitizer: Sanitizing data for anonymizing sensitive information
This is done in a two-step process: first, we develop a method that encodes unstructured image-like modality into a structured representation bifurcated by sensitive and non-sensitive representation.
Parallel Quasi-concave set optimization: A new frontier that scales without needing submodularity
We provide a parallel algorithm with a time complexity over $n$ processors of $\mathcal{O}(n^2g) +\mathcal{O}(\log{\log{n}})$ where $n$ is the cardinality of the ground set and $g$ is the complexity to compute the monotone linkage function that induces a corresponding quasi-concave set function via a duality.
Vaccination Worldwide: Strategies, Distribution and Challenges
It is a bane of the \"uber connected world that we live in that this virus has affected almost all countries and caused mortality and economic upheaval at a scale whose effects are going to be felt for generations to come.
Automatic calibration of time of flight based non-line-of-sight reconstruction
Time of flight based Non-line-of-sight (NLOS) imaging approaches require precise calibration of illumination and detector positions on the visible scene to produce reasonable results.
Can Self Reported Symptoms Predict Daily COVID-19 Cases?
The models are developed at two levels of data granularity - local models, which are trained at the state level, and a single global model which is trained on the combined data aggregated across all states.
AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning
In AirMixML, multiple workers transmit analog-modulated signals of their private data samples to an edge server who trains an ML model using the received noisy-and superpositioned samples.
PrivateMail: Supervised Manifold Learning of Deep Features With Differential Privacy for Image Retrieval
1) We present a novel differentially private method \textit{PrivateMail} for supervised manifold learning, the first of its kind to our knowledge.
MIT SafePaths Card (MiSaCa): Augmenting Paper Based Vaccination Cards with Printed Codes
In this early draft, we describe a user-centric, card-based system for vaccine distribution.
Computers and Society Cryptography and Security
COVID-19 Tests Gone Rogue: Privacy, Efficacy, Mismanagement and Misunderstandings
In this work, we discuss challenges complicating the existing covid-19 testing ecosystem and highlight the need to improve the testing experience for the user and reduce privacy invasions.
Computers and Society
Objects As Cameras: Estimating High-Frequency Illumination From Shadows
We recover high-frequency information encoded in the shadows cast by an object to estimate a hemispherical photograph from the viewpoint of the object, effectively turning objects into cameras.
COVID-19 Outbreak Prediction and Analysis using Self Reported Symptoms
In this study, we understand trends in the spread of COVID-19 by utilizing the results of self-reported COVID-19 symptoms surveys as an alternative to COVID-19 testing reports.
DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks
Recent deep learning models have shown remarkable performance in image classification.
Digital Landscape of COVID-19 Testing: Challenges and Opportunities
We summarize the challenges experienced using these tools in terms of quality of information, privacy, and user-centric issues.
Computers and Society
Challenges of Equitable Vaccine Distribution in the COVID-19 Pandemic
The COVID-19 pandemic has led to a need for widespread and rapid vaccine development.
Clinical Landscape of COVID-19 Testing: Difficult Choices
The coronavirus disease 2019 (COVID-19) pandemic has spread rapidly across the world, leading to enormous amounts of human death and economic loss.
Proximity Inference with Wifi-Colocation during the COVID-19 Pandemic
In this work we propose a WiFi colocation methodology for digital contact tracing.
Computers and Society Signal Processing
Proximity Sensing: Modeling and Understanding Noisy RSSI-BLE Signals and Other Mobile Sensor Data for Digital Contact Tracing
As we await a vaccine, social-distancing via efficient contact tracing has emerged as the primary health strategy to dampen the spread of COVID-19.
NoPeek: Information leakage reduction to share activations in distributed deep learning
For distributed machine learning with sensitive data, we demonstrate how minimizing distance correlation between raw data and intermediary representations reduces leakage of sensitive raw data patterns across client communications while maintaining model accuracy.
SplitNN-driven Vertical Partitioning
In this work, we introduce SplitNN-driven Vertical Partitioning, a configuration of a distributed deep learning method called SplitNN to facilitate learning from vertically distributed features.
FedML: A Research Library and Benchmark for Federated Machine Learning
Federated learning (FL) is a rapidly growing research field in machine learning.
Splintering with distributions: A stochastic decoy scheme for private computation
Performing computations while maintaining privacy is an important problem in todays distributed machine learning solutions.
Automatic Differentiation for All Photons Imaging to See Inside Volumetric Scattering Media
Imaging through dense scattering media - such as biological tissue, fog, and smoke - has applications in the medical and robotics fields.
Privacy Guidelines for Contact Tracing Applications
Due to this there is an emergence of mobile based applications for contact tracing.
Privacy in Deep Learning: A Survey
In this survey, we review the privacy concerns brought by deep learning, and the mitigating techniques introduced to tackle these issues.
Apps Gone Rogue: Maintaining Personal Privacy in an Epidemic
Containment, the key strategy in quickly halting an epidemic, requires rapid identification and quarantine of the infected individuals, determination of whom they have had close contact with in the previous days and weeks, and decontamination of locations the infected individual has visited.
Cryptography and Security Computers and Society Distributed, Parallel, and Cluster Computing
Split Learning for collaborative deep learning in healthcare
Shortage of labeled data has been holding the surge of deep learning in healthcare back, as sample sizes are often small, patient information cannot be shared openly, and multi-center collaborative studies are a burden to set up.
Advances and Open Problems in Federated Learning
FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches.
Recent Advances in Imaging Around Corners
Seeing around corners, also known as non-line-of-sight (NLOS) imaging is a computational method to resolve or recover objects hidden around corners.
ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations
Recently, there has been the development of Split Learning, a framework for distributed computation where model components are split between the client and server (Vepakomma et al., 2018b).
ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries
In this work we introduce ExpertMatcher, a method for automating deep learning model selection using autoencoders.
Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest
In this paper we investigate the usage of adversarial perturbations for the purpose of privacy from human perception and model (machine) based detection.
Detailed comparison of communication efficiency of split learning and federated learning
We compare communication efficiencies of two compelling distributed machine learning approaches of split learning and federated learning.
Data Markets to support AI for All: Pricing, Valuation and Governance
We discuss a data market technique based on intrinsic (relevance and uniqueness) as well as extrinsic value (influenced by supply and demand) of data.
Light-Field for RF
In the context of imaging, RF spectrum holds many advantages compared to visible light systems.
No Peek: A Survey of private distributed deep learning
We survey distributed deep learning models for training or inference without accessing raw data from clients.
A Review of Homomorphic Encryption Libraries for Secure Computation
In this paper we provide a survey of various libraries for homomorphic encryption.
Cryptography and Security
Split learning for health: Distributed deep learning without sharing raw patient data
Can health entities collaboratively train deep learning models without sharing sensitive raw data?
Maximum-Entropy Fine Grained Classification
Fine-Grained Visual Classification (FGVC) is an important computer vision problem that involves small diversity within the different classes, and often requires expert annotators to collect data.
Ranked #16 on
Fine-Grained Image Classification
on NABirds
(using extra training data)
3D Traffic Simulation for Autonomous Vehicles in Unity and Python
Over the recent years, there has been an explosion of studies on autonomous vehicles.
Flash Photography for Data-Driven Hidden Scene Recovery
The method is able to localize 12cm wide hidden objects in 2D with 1. 7cm accuracy.
Distributed learning of deep neural network over multiple agents
Our algorithm paves the way for distributed training of deep neural networks in data sensitive applications when raw data may not be shared directly.
Maximum-Entropy Fine-Grained Classification
Fine-Grained Visual Classification (FGVC) is an important computer vision problem that involves small diversity within the different classes, and often requires expert annotators to collect data.
DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images
We present the DeepGlobe 2018 Satellite Image Understanding Challenge, which includes three public competitions for segmentation, detection, and classification tasks on satellite images.
Learning Gaze Transitions From Depth to Improve Video Saliency Estimation
In this paper we introduce a novel Depth-Aware Video Saliency approach to predict human focus of attention when viewing videos that contain a depth map (RGBD) on a 2D screen.
Accelerating Neural Architecture Search using Performance Prediction
Methods for neural network hyperparameter optimization and meta-modeling are computationally expensive due to the need to train a large number of model configurations.
Pairwise Confusion for Fine-Grained Visual Classification
Fine-Grained Visual Classification (FGVC) datasets contain small sample sizes, along with significant intra-class variation and inter-class similarity.
Ranked #15 on
Fine-Grained Image Classification
on Stanford Dogs
Sampling Without Time: Recovering Echoes of Light via Temporal Phase Retrieval
This topic has its roots in the problem of recovering multiple echoes of light from its low-pass filtered and auto-correlated, time-domain measurements.
Designing Neural Network Architectures using Reinforcement Learning
We introduce MetaQNN, a meta-modeling algorithm based on reinforcement learning to automatically generate high-performing CNN architectures for a given learning task.
Lensless Imaging with Compressive Ultrafast Sensing
Each sensor acquisition is encoded with a different illumination pattern and produces a time series where time is a function of the photon's origin in the scene.
Deep Learning the City : Quantifying Urban Perception At A Global Scale
Computer vision methods that quantify the perception of urban environment are increasingly being used to study the relationship between a city's physical appearance and the behavior and health of its residents.
Macroscopic Interferometry: Rethinking Depth Estimation With Frequency-Domain Time-Of-Flight
A form of meter-scale, macroscopic interferometry is proposed using conventional time-of-flight (ToF) sensors.
Shape from Mixed Polarization
In this paper, we propose a new method that jointly uses viewpoint and polarization data to holistically separate diffuse and specular components, recover refractive index, and ultimately recover 3D shape.
Sweep Distortion Removal from THz Images via Blind Demodulation
Heavy sweep distortion induced by alignments and inter-reflections of layers of a sample is a major burden in recovering 2D and 3D information in time resolved spectral imaging.
Multi-velocity neural networks for gesture recognition in videos
We present a new action recognition deep neural network which adaptively learns the best action velocities in addition to the classification.
Deep video gesture recognition using illumination invariants
In this paper we present architectures based on deep neural nets for gesture recognition in videos, which are invariant to local scaling.
Depth Map Estimation and Colorization of Anaglyph Images Using Local Color Prior and Reverse Intensity Distribution
In this paper, we present a joint iterative anaglyph stereo matching and colorization framework for obtaining a set of disparity maps and colorized images.
Polarized 3D: High-Quality Depth Sensing With Polarization Cues
We propose a framework to overcome these key challenges, allowing the benefits of polarization to be used to enhance depth maps.
Coreset-Based Adaptive Tracking
We propose a method for learning from streaming visual data using a compact, constant size representation of all the data that was seen until a given moment.
A Light Transport Model for Mitigating Multipath Interference in Time-of-Flight Sensors
Continuous-wave Time-of-flight (TOF) range imaging has become a commercially viable technology with many applications in computer vision and graphics.
Frequency Domain TOF: Encoding Object Depth in Modulation Frequency
Time of flight cameras may emerge as the 3-D sensor of choice.
A Light Transport Model for Mitigating Multipath Interference in TOF Sensors
Continuous-wave Time-of-flight (TOF) range imaging has become a commercially viable technology with many applications in computer vision and graphics.
Resolving Multi-path Interference in Time-of-Flight Imaging via Modulation Frequency Diversity and Sparse Regularization
Time-of-flight (ToF) cameras calculate depth maps by reconstructing phase shifts of amplitude-modulated signals.
Discovering the Structure of a Planar Mirror System from Multiple Observations of a Single Point
We investigate the problem of identifying the position of a viewer inside a room of planar mirrors with unknown geometry in conjunction with the room's shape parameters.
