N
Nataraj Jammalamadaka
Researcher at International Institute of Information Technology, Hyderabad
Publications - 11
Citations - 536
Nataraj Jammalamadaka is an academic researcher from International Institute of Information Technology, Hyderabad. The author has contributed to research in topics: Pose & Deep learning. The author has an hindex of 8, co-authored 11 publications receiving 355 citations. Previous affiliations of Nataraj Jammalamadaka include Indian Institutes of Information Technology & Intel.
Papers
More filters
Book ChapterDOI
Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-Out Classifiers
TL;DR: The authors proposed an ensemble of classifiers to detect out-of-distribution (OOD) inputs using a margin-based loss over the softmax output which seeks to maintain at least a margin m between the average entropy of the OOD and in-dist distribution samples in conjunction with the standard cross-entropy loss.
Posted Content
A Study of BFLOAT16 for Deep Learning Training
Dhiraj D. Kalamkar,Dheevatsa Mudigere,Naveen Mellempudi,Dipankar Das,Kunal Banerjee,Sasikanth Avancha,Dharma Teja Vooturi,Nataraj Jammalamadaka,Jianyu Huang,Hector Yuen,Jiyan Yang,Jongsoo Park,Alexander Heinecke,Evangelos Georganas,Sudarshan Srinivasan,Abhisek Kundu,Misha Smelyanskiy,Bharat Kaul,Pradeep Dubey +18 more
TL;DR: The results show that deep learning training using BFLOAT16 tensors achieves the same state-of-the-art (SOTA) results across domains as FP32 tensors in the same number of iterations and with no changes to hyper-parameters.
Posted Content
Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers
TL;DR: A novel margin-based loss over the softmax output which seeks to maintain at least a margin m between the average entropy of the OOD and in-distribution samples and a novel method to combine the outputs of the ensemble of classifiers to obtain OOD detection score and class prediction.
Book ChapterDOI
Has my algorithm succeeded? an evaluator for human pose estimators
TL;DR: This paper proposes evaluator algorithms that predict if a vision algorithm has succeeded, and illustrates this idea for the case of Human Pose Estimation with four recently developed HPE algorithms.
Proceedings ArticleDOI
Video retrieval by mimicking poses
TL;DR: A method for real time video retrieval where the task is to match the 2D human pose of a query using a random forest of K-D trees and it is shown that pose retrieval can proceed using a low dimensional representation.