DPA: A one-stop metric to measure bias amplification in classification datasets
TBA
Education
- Ph.D in Computer Science, Arizona State University, 2028 (expected)
- M.S. in Computer Science (Big Data Systems), Arizona State University, 2024
- B.E. in Computer Engineering, Netaji Subhas Institute of Technology (now NSUT), 2018
Research & Work Experience
- Graduate Research Assistant, Arizona State University — May 2023 – Dec 2023
- Designed an automated QA/QC pipeline reducing noisy downstream data by ~90%.
- Developed semantic segmentation models for crop phenotyping and benchmarked depth-estimation models in outdoor environments.
- Research Intern, Carnegie Mellon University (remote) — Feb 2021 – Sep 2021
- Benchmarked image manipulation methods using latent-space perturbations.
- Reduced training time by ~70% via efficient sampling strategies.
- Other projects & competitions
- DARPA AI for Critical Mineral Assessment 2022 — 8th in map feature extraction challenge.
- Smart India Hackathon 2020 — National winner (real-time eye-gaze correction for video conferencing).
Teaching
- Teaching Assistant, CSE 475: Foundations of ML — Fall 2024
- Teaching Assistant, CSE 579: Intro to ML for Remote Sensing — Spring 2024
- Grader, CSE 475: Foundations of ML — Fall 2023
- Grader, CSE 572: Data Mining — Spring 2023
Skills
- Languages: Python, C++
- Machine Learning / Frameworks: PyTorch, TensorFlow / Keras, Hugging Face, scikit-learn, OpenCV
- Data & Analysis: Pandas, NumPy, Matplotlib
- Web / Tools: Flask, Selenium
- Systems & DevOps: Git, Linux, Docker
Publications
Classification Drives Geographic Bias in Street Scene Segmentation
Nair, R., Tokas, B., Tseng, G., Rolf, E., & Kerner, H. (2025). Classification Drives Geographic Bias in Street Scene Segmentation. In Proceedings of the Computer Vision and Pattern Recognition Conference (pp. 629–638).
Helmets Labeling Crops: Kenya Crop Type Dataset Created via Helmet-Mounted Cameras and Deep Learning
Nakalembe, C., Zvonkov, I., Kerner, H., Frimpong, D., Mwangi, K., Kioko, J., Tokas, B., Jawanjal, K., Smith, I., Paliyam, A., & others (2025). Helmets Labeling Crops: Kenya Crop Type Dataset Created via Helmet-Mounted Cameras and Deep Learning. Scientific Data, 12(1), 1496.
HEVC based tampered video database development for forensic investigation
Singla, N., Singh, J., Nagpal, S., & Tokas, B. (2023). HEVC based tampered video database development for forensic investigation. Multimedia Tools and Applications, 1–34.