Mahesh's webpage

301B Davis Hall

UB North Campus

Amherst, NY, 14260.

I am First year CS PhD student advised by Dr. David doermann. Prior to this, I completed my Masters in CS, also at UB, and B.Tech at Walchand College of Engineering, Shivaji University, India. I developed deep-learning models for filesystems at Veritas Technologies LLC, where I was fortunate to be advised by Anindya Banerjee.

My current research projects focus on utilizing generative models to enhance image analysis and interpretation.

Education

PhD in Computer Science - University at Buffalo, The State University of New York (2023 - Expected 2027)
Masters in Computer Science - University at Buffalo, The State University of New York (2021 - 2023)
B.Tech in Information Technology - Walchand College of Engineering, Shivaji University, India (2013-2017)

Professional Experience

Research Assistant - A2IL lab, University at Buffalo (2022 - Present)
Software Engineer - Veritas Technologies LLC (2017 - 2021)
Worked on developing deep-learning models for storage filesystems and debugging filesystem kernels.

news

Nov 15, 2024	Two papers submitted to CVPR 2025, including one first author paper on histopathology image synthesis.
Apr 20, 2024	One paper accepted to ICDAR 2024.

latest posts

Nov 28, 2024	Distance metric for fairness in vision language models
Nov 28, 2024	Quotodian commands
Nov 28, 2024	Diffusion Models Background and Code

selected publications

ICDAR 2024
ChartReformer: Natural Language-Driven Chart Image Editing

Pengyu Yan, Mahesh Bhosale, Jay Lal, and 2 more authors

In Document Analysis and Recognition - ICDAR 2024 , 2024

Abs Bib HTML

Chart visualizations are essential for data interpretation and communication; however, most charts are only accessible in image format and lack the corresponding data tables and supplementary information, making it difficult to alter their appearance for different scenarios of application. To eliminate the need for original underlying data and information to perform chart editing, we propose ChartReformer, a natural language-driven chart image editing solution that directly edits the charts from the input images with the given instruction prompts. Instead of predicting the plotting code, the key in this method is that we allow the model to comprehend the chart and reason over the prompt to generate the corresponding underlying data table and visual attributes for new charts, enabling a precise and stable editing result. To generalize ChartReformer, we define and standardize the chart editing category and generate the ChartCraft dataset, covering style, layout, format, and data-centric edits. The experiments show promising results for the natural language-driven chart image editing. Our datasets and model are available at: https://github.com/pengyu965/ChartReformer.
@inproceedings{10.1007/978-3-031-70533-5_26, author = {Yan, Pengyu and Bhosale, Mahesh and Lal, Jay and Adhikari, Bikhyat and Doermann, David}, editor = {Barney Smith, Elisa H. and Liwicki, Marcus and Peng, Liangrui}, title = {ChartReformer: Natural Language-Driven Chart Image Editing}, booktitle = {Document Analysis and Recognition - ICDAR 2024}, year = {2024}, publisher = {Springer Nature Switzerland}, address = {Cham}, pages = {453--469}, isbn = {978-3-031-70533-5}, url = {https://link.springer.com/chapter/10.1007/978-3-031-70533-5_26}, }
ICDAR 2023
LineFormer: Line Chart Data Extraction Using Instance Segmentation

Jay Lal, Mahesh Bhosale, Aditya Mitkari, and 1 more author

In Document Analysis and Recognition - ICDAR 2023 , 2023

Abs Bib HTML

Data extraction from line-chart images is an essential component of the automated document understanding process, as line charts are a ubiquitous data visualization format. However, the amount of visual and structural variations in multi-line graphs makes them particularly challenging for automated parsing. Existing works, however, are not robust to all these variations, either taking an all-chart unified approach or relying on auxiliary information such as legends for line data extraction. In this work, we propose LineFormer, a robust approach to line data extraction using instance segmentation. We achieve state-of-the-art performance on several benchmark synthetic and real chart datasets. Our implementation is available at https://github.com/TheJaeLal/LineFormer.
@inproceedings{10.1007/978-3-031-41734-4_24, author = {Lal, Jay and Bhosale, Mahesh and Mitkari, Aditya and Doermann, David}, editor = {Fink, Gernot A. and Jain, Rajiv and Kise, Koichi and Zanibbi, Richard}, title = {LineFormer: Line Chart Data Extraction Using Instance Segmentation}, booktitle = {Document Analysis and Recognition - ICDAR 2023}, year = {2023}, publisher = {Springer Nature Switzerland}, address = {Cham}, pages = {387--400}, isbn = {978-3-031-41734-4}, url = {https://link.springer.com/chapter/10.1007/978-3-031-41734-4_24}, }