no code implementations • 22 May 2022 • Vamshi C. Madala, Shivkumar Chandrasekaran, Jason Bunk
A priori theories explaining the generalization performances of deep neural networks have mostly ignored the convolutionality aspect and do not specify why CNNs are able to seemingly overcome curse of dimensionality on computer vision tasks like image classification where the image dimensions are in thousands.
no code implementations • 22 Mar 2021 • Jason Bunk, Srinjoy Chattopadhyay, B. S. Manjunath, Shivkumar Chandrasekaran
Mixup is a procedure for data augmentation that trains networks to make smoothly interpolated predictions between datapoints.
1 code implementation • 19 Mar 2021 • Michael Goebel, Jason Bunk, Srinjoy Chattopadhyay, Lakshmanan Nataraj, Shivkumar Chandrasekaran, B. S. Manjunath
Machine Learning (ML) algorithms are susceptible to adversarial attacks and deception both during training and deployment.
no code implementations • 1 Mar 2018 • Arjuna Flenner, Lawrence Peterson, Jason Bunk, Tajuddin Manhar Mohammed, Lakshmanan Nataraj, B. S. Manjunath
A deep learning classifier is then used to generate a heatmap that indicates if the image block has been resampled.
no code implementations • 9 Feb 2018 • Tajuddin Manhar Mohammed, Jason Bunk, Lakshmanan Nataraj, Jawadul H. Bappy, Arjuna Flenner, B. S. Manjunath, Shivkumar Chandrasekaran, Amit K. Roy-Chowdhury, Lawrence Peterson
Realistic image forgeries involve a combination of splicing, resampling, cloning, region removal and other methods.
no code implementations • ICCV 2017 • Jawadul H. Bappy, Amit K. Roy-Chowdhury, Jason Bunk, Lakshmanan Nataraj, B. S. Manjunath
In order to formulate the framework, we employ a hybrid CNN-LSTM model to capture discriminative features between manipulated and non-manipulated regions.
1 code implementation • 3 Jul 2017 • Jason Bunk, Jawadul H. Bappy, Tajuddin Manhar Mohammed, Lakshmanan Nataraj, Arjuna Flenner, B. S. Manjunath, Shivkumar Chandrasekaran, Amit K. Roy-Chowdhury, Lawrence Peterson
In this paper, we propose two methods to detect and localize image manipulations based on a combination of resampling features and deep learning.