Tarun Kalluri

I am a fourth-year PhD student in the CSE department at UCSD advised by Prof. Manmohan Chandrakar. My research interests span the areas of computer vision and machine learning. I am interested in learning representations of images and videos from limited labeled data that are useful and transferable across a wide range of domains. Specifically, I work on problems in domain adaptation, transfer learning, few shot learning and open world learning.

Previously, I worked as a research assistant at Centre for Visual Information and Technology (CVIT), IIIT Hyderabad on various problems related to semantic understanding from large scale text and image data. I completed my undergraduate studies from IIT Guwahati in 2016, before working as a data scientist at Oracle Bangalore where I was part of team responsible for creating automated client-side cloud instance provisioning, upgrade and patching tools.

Tarun Kalluri

Email / CV / Google Scholar / GitHub / LinkedIn / Twitter

I am looking for research internships starting in spring 2023! Please reach out to me if you have open positions and similar interests as mine.

August 2022: One paper on video frame interpolation accepted to WACV 2023.
July 2022: One paper on domain adaptation accepted to ECCV 2022.
May 2022: Selected as Highlighted reviewer at ICLR2022.
June 2021: Started internship at FAIR, MPK to work on open-world learning.
May 2021: One paper on domain adaptation accepted at CVPR 2021!
Sep 2020: Recipient of IPE PhD fellowship for the year 2020-21.
Aug 2020: Our paper on training neural network for molecular force predictions is accepted to the Journal of Physical Chemistry.
June 2020: Joined Facebook AI as a summer intern with the multimodal learning group.
Dec 2019: One paper on datasets for resource constrained semantic segmentation accepted to NCVPRIPG 2019.
Sep 2019: Moved to sunny San Diego! Starting as a PhD student at CSE department in UCSD from Fall 2019. I will be working with the Visual Computing Group.
Jul 2019: Our paper on Universal Semantic Segmentation is accepted to ICCV 2019.

MemSAC: Memory Augmented Sample Consistency for Large Scale Domain Adaptation
Tarun Kalluri , Astuti Sharma, Manmohan Chandraker.
ECCV, 2022
webpage / arxiv / pdf / code / reviews / poster /

Memory-based consistency losses to scale unsupervised domain adaptation to a large number of classes, including fine-grained datasets.

FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation
Tarun Kalluri , Deepak Pathak, Manmohan Chandraker, Du Tran
WACV, 2023
arxiv / pdf / project webpage / video / Code/ reviews / Colab

Fast, accurate and flow-free video frame interpolation technique using space-time convolutions, capable of single shot multi frame prediction.

Cluster-to-adapt: Few Shot Domain Adaptation for Semantic Segmentation across Disjoint Labels
Tarun Kalluri , Manmohan Chandraker.
L3D Workshop, CVPR, 2022
pdf / poster

Domain adaptation across datasets with disjoint labels using a deep-clustering based approach and an intermediate bridge domain.

Instance Level Affinity Based Transfer for Unsupervised Domain Adaptation
Astuti Sharma, Tarun Kalluri , Manmohan Chandraker.
CVPR, 2021
arxiv / code

Proposes multi sample contrastive loss using instance level similarities across source and target domains for robust feature alignment and knowledge transfer.

Universal Semi-Supervised Semantic Segmentation
Tarun Kalluri , Girish Varma, Manmohan Chandraker, CV Jawahar
ICCV, 2019
pdf / poster / reviews / code

Addresses geographical disparities between semantic segmentation datasets with minimum labeling overhead from each domain.

Machine Learning for Accurate Force Calculations in Molecular Dynamics Simulations
Punyaslok Pattnaik, Shampa Raghunathan, Tarun Kalluri , Prabhakar Bhimalapuram, C. V. Jawahar, U. Deva Priyakumar
Jorurnal of Physical Chemistry A, 2020
pdf / chemRxiv

Neural network aided simulation of molecular forces making use of the data obtained using the quantummechanical density functional theory (DFT) on small systems.

Semantic Segmentation Datasets for Resource Constrained Training
Ashutosh Mishra*, Sudhir Kumar*, Tarun Kalluri* , Girish Varma, Anbumani Subramaian, Manmohan Chandraker, CV Jawahar
pdf / poster / reviews / dataset

Proposes optimum model and data resampling choices for resource constrained training of semantic segmentation networks.

Cooperative Spectrum Sharing-based Relaying Protocols with Wireless Energy Harvesting Cognitive User
Tarun Kalluri , Mansi Peer, Vivek Bohara, Daniel B. da Costa, Ugo S. Dias
IET Communications, 2018

Relaying protocols for energy harvesting wireless sensor networks under cooperative spectrum sharing.


In the past, I have been extremely fortunate to have been advised by the following mentors.

[3] Domain adaptation for urban scene understanding, Augmented Reality and Self-Driving workshop, Qualcomm San Diego, June 2020 [slides][abstract]
[2] Cross Task Adaptation for semantic segmentation, Pixel Cafe, UCSD, May 2020
[1] Universal Semi-supervised Semantic Segmentation, Pixel Cafe, UCSD, Nov 2019 [slides]

Template modified from Jon Barron and Micheal Hahn