1 code implementation • 11 Sep 2020 • Yichuan Liu, Hailey James, Otkrist Gupta, Dan Raviv
Detecting and extracting information from Machine-Readable Zone (MRZ) on passports and visas is becoming increasingly important for verifying document authenticity.
Optical Character Recognition Optical Character Recognition (OCR)
no code implementations • 10 Sep 2020 • Hailey James, Otkrist Gupta, Dan Raviv
Detecting manipulations in digital documents is becoming increasingly important for information verification purposes.
Optical Character Recognition Optical Character Recognition (OCR)
1 code implementation • 20 Aug 2020 • Praneeth Vepakomma, Abhishek Singh, Otkrist Gupta, Ramesh Raskar
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.
no code implementations • 27 Apr 2020 • Hailey James, Otkrist Gupta, Dan Raviv
Of the three models, our proposed model outperforms the others when trained and validated on images from a single printer.
no code implementations • 27 Sep 2019 • Indu Ilanchezian, Praneeth Vepakomma, Abhishek Singh, Otkrist Gupta, G. N. Srinivasa Prasanna, Ramesh Raskar
In this paper we investigate the usage of adversarial perturbations for the purpose of privacy from human perception and model (machine) based detection.
no code implementations • 18 Sep 2019 • Abhishek Singh, Praneeth Vepakomma, Otkrist Gupta, Ramesh Raskar
We compare communication efficiencies of two compelling distributed machine learning approaches of split learning and federated learning.
no code implementations • 8 Dec 2018 • Praneeth Vepakomma, Tristan Swedish, Ramesh Raskar, Otkrist Gupta, Abhimanyu Dubey
We survey distributed deep learning models for training or inference without accessing raw data from clients.
1 code implementation • 3 Dec 2018 • Praneeth Vepakomma, Otkrist Gupta, Tristan Swedish, Ramesh Raskar
Can health entities collaboratively train deep learning models without sharing sensitive raw data?
no code implementations • NeurIPS 2018 • Abhimanyu Dubey, Otkrist Gupta, Ramesh Raskar, Nikhil Naik
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 #19 on Fine-Grained Image Classification on NABirds (using extra training data)
no code implementations • 14 Oct 2018 • Otkrist Gupta, Ramesh Raskar
Our algorithm paves the way for distributed training of deep neural networks in data sensitive applications when raw data may not be shared directly.
no code implementations • 16 Sep 2018 • Abhimanyu Dubey, Otkrist Gupta, Ramesh Raskar, Nikhil Naik
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.
2 code implementations • ICLR 2018 • Bowen Baker, Otkrist Gupta, Ramesh Raskar, Nikhil Naik
Methods for neural network hyperparameter optimization and meta-modeling are computationally expensive due to the need to train a large number of model configurations.
1 code implementation • ECCV 2018 • Abhimanyu Dubey, Otkrist Gupta, Pei Guo, Ramesh Raskar, Ryan Farrell, Nikhil Naik
Fine-Grained Visual Classification (FGVC) datasets contain small sample sizes, along with significant intra-class variation and inter-class similarity.
Ranked #16 on Fine-Grained Image Classification on Stanford Dogs
5 code implementations • 7 Nov 2016 • Bowen Baker, Otkrist Gupta, Nikhil Naik, Ramesh Raskar
We introduce MetaQNN, a meta-modeling algorithm based on reinforcement learning to automatically generate high-performing CNN architectures for a given learning task.
no code implementations • 22 Mar 2016 • Otkrist Gupta, Dan Raviv, Ramesh Raskar
We present a new action recognition deep neural network which adaptively learns the best action velocities in addition to the classification.
no code implementations • 21 Mar 2016 • Otkrist Gupta, Dan Raviv, Ramesh Raskar
In this paper we present architectures based on deep neural nets for gesture recognition in videos, which are invariant to local scaling.