Phani Krishna Uppala — accepted AI-conference papers

2018

AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation

Jogendra Nath Kundu, Phani Krishna Uppala, Anuj Pahuja, R. Venkatesh Babu

CVPR 2018poster

Supervised deep learning methods have shown promising results for the task of monocular depth estimation; but acquiring ground truth is costly, and prone to noise as well as inaccuracies. While synthetic datasets have been used to circumvent above problems, the resultant models do not generalize wel…

Cited by 218 Source ↗PDF ↗Scholar ↗

2018

Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressions

Konda Reddy Mopuri, Phani Krishna Uppala, R. Venkatesh Babu

ECCV 2018poster

Deep learning models are susceptible to input specific noise, called adversarial perturbations. Moreover, there exist input-agnostic noise, called Universal Adversarial Perturbations (UAP) that can affect inference of the models over most input samples. Given a model, there exist broadly two approac…

Cited by 113 Source ↗PDF ↗code ↗Scholar ↗