Search Results for author: Venkatesh Babu Radhakrishnan

Found 6 papers, 3 papers with code

Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metrics

1 code implementation28 Apr 2023 Harsh Rangwani, Shrinivas Ramasubramanian, Sho Takemori, Kato Takashi, Yuhei Umeda, Venkatesh Babu Radhakrishnan

Using the proposed CSST framework, we obtain practical self-training methods (for both vision and NLP tasks) for optimizing different non-decomposable metrics using deep neural networks.

Crafting Data-free Universal Adversaries with Dilate Loss

no code implementations25 Sep 2019 Deepak Babu Sam, Abinaya K, Sudharsan K A, Venkatesh Babu Radhakrishnan

We introduce a method to create Universal Adversarial Perturbations (UAP) for a given CNN in a data-free manner.

Game of Sketches: Deep Recurrent Models of Pictionary-style Word Guessing

1 code implementation29 Jan 2018 Ravi Kiran Sarvadevabhatla, Shiv Surya, Trisha Mittal, Venkatesh Babu Radhakrishnan

Similarly, performance on multi-disciplinary tasks such as Visual Question Answering (VQA) is considered a marker for gauging progress in Computer Vision.

Question Answering Test +1

DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data

2 code implementations CVPR 2017 Swaminathan Gurumurthy, Ravi Kiran Sarvadevabhatla, Venkatesh Babu Radhakrishnan

A class of recent approaches for generating images, called Generative Adversarial Networks (GAN), have been used to generate impressively realistic images of objects, bedrooms, handwritten digits and a variety of other image modalities.

Image Generation

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