• CNN Fixations - An unraveling approach to visualize the discriminative image regions

  31 Aug 2017

  [Paper] [Code] [Project Page] Abstract Deep convolutional neural networks (CNN) have revolutionized various fields of vision research and have seen unprecedented adoption for multiple tasks such as classification, detection, captioning, etc. However, they offer little transparency into their inner workings and are often treated as black boxes that provide excellent...

• GSoC 2017 - The End

  17 Aug 2017

  [Project Website] Google Summer of Code 2017 has finally come to an end and it couldn’t have been any better. The past three months have been an excellent experience working on Fabrik and it gives me great satisfaction having worked on a project which will potentially benefit a lot of...

• Fast Feature Fool - A data independent approach to universal adversarial perturbations

  23 Jul 2017

  [Paper] [Code] [Project Page] Abstract State-of-the-art object recognition Convolutional Neural Networks (CNNs) are shown to be fooled by image agnostic perturbations, called universal adversarial perturbations. It is also observed that these perturbations generalize across multiple networks trained on the same target data. However, these algorithms require training data on which...

• GSoC 2017 - First Evaluation

  24 Jun 2017

  The summer is passing by quickly and its almost time for the first evaluation. Following the first two weeks which mainly involved fixing and completing old features, the third week began with writing unit tests for backend modules. Until now the project had no unit tests and covering all the...

• GSoC 2017 - Getting Started

  10 Jun 2017

  I am working for the CloudCV organization on a project named Fabrik. The project aims at bringing down the threshold for getting started with Deep Learning by providing a drag and drop way of building neural networks, while also providing functionality to pro users for visualizing the said graphs and...