Search Results for author: Jason Bunk

Found 7 papers, 2 papers with code

CNNs Avoid Curse of Dimensionality by Learning on Patches

no code implementations22 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.

Data Augmentation Image Classification

Adversarially Optimized Mixup for Robust Classification

no code implementations22 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.

Classification Data Augmentation +2

Exploiting Spatial Structure for Localizing Manipulated Image Regions

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.

Image Manipulation Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.