Meghana Reddy Ganesina

I’m a second-year M.S. Computer Vision (MSCV) student at Robotics Institute, Carnegie Mellon University (CMU). I am working at CMU Argo AI Center for Autonomous Vehicle Research as a research collaborator, under the guidance of Prof. Deva Ramanan.

Recently, I worked at Zoox as a Prediction Machine Learning Intern. My work primarily involved designing an agent trajectory autoencoder inspired from Multi-Context Gating architecture for the downstream task of predicting consistent and diverse future agent trajectory set.

Email  |  CV  |  Google Scholar  |  Linkedin

profile photo

I am most excited about developing robust and scalable computer vision algorithms. My research at Argo AI aims at developing an approach for LiDAR panoptic segmentation in an open-world setting. Previously, I have mainly worked on facial recognition systems and classification models for medical applications.

Disguised face identification (dfi) with facial keypoints using spatial fusion convolutional network
Amarjot Singh, Devendra Patil, Meghana Reddy Ganesina, SN Omkar
Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017
[Video] [Dataset]

Developed a real-time disguised face identification system based on facial keypoint analysis using spatial Convolutional Neural Network. Furthermore, I collaborated with a team of researchers to annotate disguised face dataset to further the research.

Automatic Classification of Whole Slide Pap Smear Images using CNN with PCA based Feature Interpretation
Meghana Reddy Ganesina**, Kranthi Kiran GV** (** indicates equal contribution)
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019

Modelled a segmentation-free direct classification network to classify cervical cancerous cells which outperformed previous baselines. We observed correlations between the factors analyzed by pathologists and learned feature representations of the network.

Challenges In Power-Aware Verification with Hardware Power Controller and Novel Approach to Harness Xcelium Low-Power Functional Coverage for Complex SoC
Meghana Reddy Ganesina, Harshal.K, Sriram K.S, Somasunder Sreenath
Proceedings of CDN Live 2021: SoC Verification: Advanced Verification Methodology

This paper canvasses a strategy for Power-aware verification and discusses the steps to be followed in the run up to bring-up power aware simulations, scenarios to target for gate level with and without timing annotation, and optimizations for simulations that were done to achieve upto 52% higher performance and efficiency in the project execution.

News Updates
[Aug 2022] Check out my project page for LiDAR Panoptic Segmentation in Open World!

[May 2022] Starting a new position as Summer Intern in the Prediction team at Zoox.

[Oct 2021] Starting a new position as Research Collaborator at CMU Argo AI Center for Autonomous Vehicle Research under the guidance of Prof. Deva Ramanan.

[Aug 2021] Starting my M.S. Computer Vision (MSCV) degree at the Robotics Institute, Carnegie Mellon University (CMU).

[Aug 2018] Attended Summer Business Scholars Program at Booth school of Business, University of Chicago in 2018.

[Jun 2018] Started a new position as a Hardware Engineer in the SoC Foundry HW team at Samsung Semiconductors India R&D, bangalore.

[May 2018] Received my Bachelor's degree from National Institute of Technology Warangal, with a major in Electronics and Communication Engineering.

[May 2016] Started summer internship at Indian Institute of Science, Bangalore

Source code from Jon Barron