Aneesh Rangnekar

I am a Research Scholar at Memorial Sloan Kettering Cancer Center's Department of Medical Physics under Dr. Harini Veeraraghavan. My work is focused on machine learning for medical image analysis. Previously, I was a PhD student in The Chester F. Carlson Center for Imaging Science at Rochester Institute of Technology (RIT), where I work on developing and applying computer vision frameworks to hyperspectral imagery with my advisor, Dr. Matthew Hoffman and my co-advisor, Dr. Christopher Kanan.

Email (MSKCC) / Email (Personal) / Google Scholar / Github

Research

	3D Swin Transformer for Partial Medical Auto Segmentation Aneesh Rangnekar, Jue Jiang, Harini Veeraraghavan MICCAI 2023 FLARE Challenge, 2023 code To be filled.
	Semantic Segmentation with Active Semi-Supervised Learning Aneesh Rangnekar, Christopher Kanan, Matthew Hoffman Winter Conference on Applications of Computer Vision (WACV), 2023 code To be filled.
	SpecAL: Towards Active Learning for Semantic Segmentation of Hyperspectral Imagery Aneesh Rangnekar, Emmett Ientilucci, Christopher Kanan, Matthew Hoffman International Conference on Dynamic Data Driven Application Systems (DDDAS), 2022 Paper To be filled.
	Semantic Segmentation with Active Semi-Supervised Representation Learning Aneesh Rangnekar, Christopher Kanan, Matthew Hoffman British Machine Vision Conference (BMVC), 2022 code To be filled.
	Semi-Supervised Hyperspectral Object Detection Challenge Results - PBVS 2022 Aneesh Rangnekar, Zachary Mulhollan, Anthony Vodacek, Matthew Hoffman, Angel Sappa, Erik Blasch, Jun Yu, Liwen Zhang, Shenshen Du, Hao Chang, Keda Lu, Zhong Zhang, Fang Gao, Ye Yu, Feng Shuang, Lei Wang, Qiang Ling, Pranjay Shyam, Kuk-Jin Yoon, Kyung-Soo Kim Perception Beyond the Visible Spectrum (PBVS-CVPRW), 2022 We summarize the results of the first semi-supervised hyperspectral object detection challenge as a part of the PBVS workshop at CVPR.
	Hyperspectral Camera Characterization of System Spectral Radiance Error for Spectral Identification of Reflective Objects Using Aerial Imagery Zachary Mulhollan, Donald McKeown, Anthony Vodacek, Aneesh Rangnekar, Matthew Hoffman AGU Fall Meeting, 2021 We define and implement a spectral radiative transfer calibration image processing procedure for multispectral and hyperspectral imaging systems with a global shutter.
	Fine-Tuning for One-Look Regression Vehicle Counting in Low-Shot Aerial Datasets Aneesh Rangnekar, Yi Yao, Matthew Hoffman, Ajay Divakaran Workshop on Analysis of Aerial Motion Imagery (WAAMI-ICPRW), 2020 Paper We investigate the task of entity counting in overhead imagery from the perspective of re-purposing representations learned from ground imagery, e.g., ImageNet, via feature adaptation.
	AeroRIT: A New Scene for Hyperspectral Image Analysis Aneesh Rangnekar, Nilay Mokashi, Emmett Ientilucci, Christopher Kanan, Matthew Hoffman Transactions on Geoscience and Remote Sensing (TGRS), 2020 arXiv / code We investigate applying different semantic segmentation architectures to the AeroRIT flight line by labeling every pixel for semantic scene understanding.
	Uncertainty Estimation for Semantic Segmentation of Hyperspectral Imagery Aneesh Rangnekar, Emmett Ientilucci, Christopher Kanan, Matthew Hoffman International Conference on Dynamic Data Driven Application Systems (DDDAS), 2020 Paper We investigate and adapt different existing frameworks for uncertainty quantification for semantic segmentation of hyperspectral imagery.
	Occlusion Detection for Dynamic Adaptation Zachary Mulhollan, Aneesh Rangnekar, Anthony Vodacek, Matthew Hoffman International Conference on Dynamic Data Driven Application Systems (DDDAS), 2020 Paper We create a synthetic environment to map terrain and find occluded regions in the scene by integrating streams of real data with a physics-based simulation model that updates based on the most recent set of images.
	Calibrated Vehicle Paint Signatures for Simulating Hyperspectral Imagery Zachary Mulhollan, Aneesh Rangnekar, Timothy Bauch, Matthew Hoffman, Anthony Vodacek Perception Beyond the Visible Spectrum (PBVS-CVPRW), 2020 We investigate a procedure for rapidly adding calibrated vehicle visible-near infrared (VNIR) paint signatures to an existing hyperspectral simulator - The Digital Imaging and Remote Sensing Image Generation (DIRSIG) model - to create more diversity in simulated urban scenes.
	Tracking in Aerial Hyperspectral Videos Using Deep Kernelized Correlation Filters Burak Uzkent, Aneesh Rangnekar, Matthew Hoffman Transactions on Geoscience and Remote Sensing (TGRS), 2018 arXiv / code We develop the Deep Hyperspectral Kernelized Correlation Filter based tracker (DeepHKCF) to efficiently track aerial vehicles using an adaptive multi-modal hyperspectral sensor.
	Aerial Spectral Super-Resolution using Conditional Adversarial Networks Aneesh Rangnekar, Nilay Mokashi, Emmett Ientilucci, Christopher Kanan, Matthew Hoffman arXiv, 2017 We train a conditional adversarial network to learn an inverse mapping from a trichromatic space to 31 spectral bands within 400 to 700 nm.
	Aerial Vehicle Tracking by Adaptive Fusion of Hyperspectral Likelihood Maps Burak Uzkent, Aneesh Rangnekar, Matthew Hoffman Perception Beyond the Visible Spectrum (PBVS-CVPRW), 2017 code We propose a novel real-time hyperspectral likelihood maps-aided target detection and tracking method (HLT) inspired by an adaptive hyperspectral sensor.

This website is adapted from Jon Barron's template (site, source code)