Sagar Verma

CTO & Co-Founder
Granular AI
Bostom, MA, U.S.A / Paris, France

I completed my Ph.D. under Dr. Jean-Christophe Pesquet on neural network pruning for time-series applications. As part of my Ph.D., I worked on modeling the dynamics of heavy electrical motors using neural networks under the guidance of Dr. Marc Castella, Nicolas Henwood, and Al-Kassem Jebai. I am CTO and Co-Founder of Granular AI. At Granular AI our goal is to democratize Geospatial Machine Learning. We are making an open source platform for geospatial researchers and developers.

I was a Junior Research Fellow at Computer Vision and Machine Learning Lab (IIIT Delhi) under Dr. Chetan Arora where I worked on egocentric video understanding. I have worked with Dr. Angshul Majumdar on applications of generative models to collaborative filtering and energy management systems. I have also worked with Dr. P.B. Sujit on reinforcement learning for control problems. I completed M. Tech. in 2017 from IIIT-Delhi.

News

Publications


S. Goswami, S. Verma, K. Gupta, and S. Gupta. FloodNet-to-FloodGAN : Generating Flood Scenes in Aerial Images., 2022 [PDF].

S. Verma, N. Henwood, M. Castella, JC Pesquet, and AK Jebai. Can GANs Recover Faults in Electrical Motor Sensors?, (Accepted in ICLR Workshop 2022) [PDF].

Shin et. al. Europa: Increasing Accessibility of Geospatial Datasets, (Accepted in IGARSS 2022) [PDF].

Verma et. al. GeoEngine: A Platform for Production-Ready Geospatial Research, (Accepted in CVPR Demo 2022) [PDF].

S. Verma, S. Singh, and A. Majumdar. Multi-label LSTM autoencoder for non-intrusive appliance load monitoring, (Accepted in EPSR 2021) [PDF].

S. Verma, N. Henwood, M. Castella, AK Jebai, and JC Pesquet. Neural Speed-Torque Estimator for Induction Motors in the Presence of Measurement Noise, (Accepted in IEEE TIE 2022) [Project Page].

S. Verma and JC Pesquet. Sparsifying Networks via Subdifferential Inclusion, (Accepted in ICML 2021) [Project Page, PDF].

S. Verma, A. Panigrahi, and S. Gupta. QFabric: Multi-Task Change Detection Dataset, (Accepted in CVPR Earthvision 2021) [Project Page, Dataset, PDF].

S. Verma, N. Henwood, M. Castella, AK Jebai, and JC Pesquet. Neural Networks based Speed-Torque Estimators for Induction Motors and Performance Metrics, (Accepted in IECON 2020) [Project Page, PDF, PPT, Video].

Lassau et. al. AI-Based Multi-Modal Integration of Clinical Characteristics, Lab Tests and Chest CTs Improves COVID19 Outcome Prediction of Hospitalized Patients, (Accepted in Nature Communications) [PDF, Code, Article in Le Monde].

S. Verma, N. Henwood, M. Castella, F. Malrait, and JC Pesquet. Modeling Electrical Motor Dynamics using Encoder-Decoder with Recurrent Skip Connection, (Accepted in AAAI 2020) [Project Page, PDF, Poster].

M. Papadomanolaki, S. Verma, M. Vakalopoulou, S. Gupta, and K. Karantzalos. Detecting Urban Changes with Recurrent Neural Networks from Multitemporal Sentinel-2 Data, (Accepted in IGARSS 2019) [PDF, PAISS Poster, code].

S. Verma, R. Verma, and P.B. Sujit. MAPEL: Multi-Agent Pursuer-Evader Learning using Situation Report, (Accepted in IJCNN 2019) [PDF].

S. Verma, S. Singh, and A. Majumdar. Multi Label Restricted Boltzmann Machine for Non-Intrusive Load Monitoring, (Accepted in ICASSP 2019) [PDF].

S. Verma, P. Nagar, D. Gupta, C. Arora. Making Third Person Techniques Recognize First-Person Actions in Egocentric Videos, (ICIP 2018) [PDF, code, poster].

S. Verma, S. Anand, C. Arora, A. Rai. Diversity in Fashion Recommendation Using Semantic Parsing, (ICIP 2018) [PDF, code, PPT].

M. Jammi, J. Sen, A. Mittal, S. Verma, V. Pahuja, R. Ananthanarayanan, P. Lohia, H. Karanam, D. Saha, K. Sankaranarayanan. Tooling Framework for Instantiating Natural Language Querying System, (VLDB, Demo Track, 2018) [PDF, code, demo].

S. Verma, P. Patel, A. Majumdar. Collaborative Filtering with Label Consistent Restricted Boltzmann Machine, (ICAPR 2017) [PDF, code].


Others


S. Verma. A Survey on Machine Learning Applied to Dynamic Physical Systems [Project Page, PDF, code].

S. Verma. Action Recognition in Egocentric Videos, (M. Tech. Thesis 2017) [IIITD archive].

Posts

Note: I write blogs to learn and practice mathematical concepts, technical writing, and aesthetic presentation. These posts should never be taken as a primary source of information. For a clear and accurate understanding, please visit citations.


Urbanization detection

Why do bi-temporal data fail in modeling urban sprawl? Introducing a large multi-date change detection dataset. Deriving urban growth index from Sentinel-2 multi-date images. Exploring U-Net, RNN, QRNN to handle multi-date input.

GAN for atmospheric correction

ESA's SAFE and DigitalGlobe's FLAME provide solutions to atmospheric correction and base layer matching problems respectively. Both are proprietary products and require intensive computing resources and are not suitable for processing large maps in limited time. Can GANs solve atmospheric correction, tile blending, and cloud correction problem?

Unsupervised LULC

Unsupervised feature learning from satellite images using cross-channel encoder based on split-brain architecture. Feature learning using hyperspectral images, constructing thermal bands from RGB and vice-versa. Normalized cuts on learned features for semantic segmentation.

Video understanding

Activity and action recognition in first-person videos. Two datasets of short and long activities in Plumbing and PC Assembling domain respectively. Baselines of two-stream CNN, I3D, SlowFast, and C3D networks.

देवनागरी

Article segmentation and word recognition in Indian regional newspapers.

Multiagent reinforcement learning

A multi-agent pursuit-evasion game with partial observability. Situation reports for sparse communication and coordinated reinforcement learning.

*Right now posts point to github repositories, details will be updated soon.