Anisha Pal

I am a machine learning researcher and engineer with a Master’s in Computer Science from Georgia Tech, where I was supervised by Prof. Judy Hoffman on problems related to robustness and distribution shift in vision systems. I have also had the unique privilege of working across a range of interdisciplinary industry settings, spanning early-stage startups to large-scale organizations, including Planette AI, Corteva Agriscience, HyperVerge, and Microsoft.

Broadly, I am interested in understanding how domain-specific structure and expert knowledge can be leveraged to build robust and interpretable machine learning systems.

Portrait of Anisha Pal

News

June, 2025 Presented Leveraging CESM2 data for machine learning based S2S forecasting at the CESM Workshop 2025
Sep, 2024 Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image Detectors is accepted to NeurIPS 2024 Track Datasets and Benchmarks
July, 2024 SkyScenes: A Synthetic Dataset for Aerial Scene Understanding is accepted to ECCV 2024
May, 2024 Joined as the Founding Machine Learning Engineer at Planette AI
May, 2023 Interning at Corteva Agriscience this summer
August, 2022 Joined the MS CS Program at Georgia Tech

Publications

Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image Detectors

Anisha Pal*, Julia Kruk*, Mansi Phute, Manognya Bhattaram, Diyi Yang, Duen Horng Chau, Judy Hoffman

NeurIPS, 2024

SkyScenes: A Synthetic Dataset for Aerial Scene Understanding

Sahil Khose*, Anisha Pal*, Aayushi Agarwal*, Deepanshi*, Judy Hoffman, Prithvijit Chattopadhyay

ECCV, 2024

SegFast-V2: Semantic Image Segmentation with Less Parameters in Deep Learning for Autonomous Driving

Swarnendu Ghosh, Anisha Pal, Shourya Jaiswal, KC Santosh, Nibaran Das, Mita Nasipuri

IJMLC, 2019

SegFast: A Faster SqueezeNet Based Semantic Image Segmentation Using Depth-wise Separable Convolutions

Anisha Pal, Shourya Jaiswal, Swarnendu Ghosh, Nibaran Das, Mita Nasipuri

ICVGIP, 2018