scispace - formally typeset
S

Siddhartha Chandra

Researcher at Amazon.com

Publications -  26
Citations -  1956

Siddhartha Chandra is an academic researcher from Amazon.com. The author has contributed to research in topics: Conditional random field & Structured prediction. The author has an hindex of 12, co-authored 24 publications receiving 1368 citations. Previous affiliations of Siddhartha Chandra include International Institute of Information Technology, Hyderabad & Supélec.

Papers
More filters
Posted ContentDOI

Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge

Spyridon Bakas, +438 more
- 05 Nov 2018 - 
TL;DR: This study assesses the state-of-the-art machine learning methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018, and investigates the challenge of identifying the best ML algorithms for each of these tasks.
Book ChapterDOI

Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs

Siddhartha Chandra, +1 more
TL;DR: This work proposes a structured prediction technique that combines the virtues of Gaussian Conditional Random Fields with Deep Learning, and develops very efficient algorithms for inference and learning, as well as a customized technique adapted to the semantic segmentation task.
Posted Content

Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs

Siddhartha Chandra, +1 more
- 28 Mar 2016 - 
TL;DR: In this paper, a structured prediction technique that combines the virtues of Gaussian Conditional Random Fields (G-CRF) with deep learning is proposed, which has a unique global optimum that is obtained exactly from the solution of a linear system and the gradients of model parameters are analytically computed using closed form expressions.
Proceedings ArticleDOI

Dense and Low-Rank Gaussian CRFs Using Deep Embeddings

Siddhartha Chandra, +2 more
TL;DR: This work introduces a structured prediction model that endows the Deep Gaussian Conditional Random Field with a densely connected graph structure, and shows that the learned embeddings capture pixel-to-pixel affinities in a task-specific manner.
Proceedings ArticleDOI

Learning to Generate Synthetic Data via Compositing

Shashank Tripathi, +5 more
TL;DR: A task-specific approach to synthetic data generation that employs a trainable synthesizer network that is optimized to produce meaningful training samples by assessing the strengths and weaknesses of a ‘target’ classifier and trained in an adversarial manner.