Publications

1. Ozturk, E., Prabhushankar, M., & AlRegib, G. (2024). Intelligent Multi-View Test Time Augmentation. arXiv preprint arXiv:2406.08593. Article Link, Code

2. Chowdhury, P., Prabhushankar, M., AlRegib, G., & Deriche, M. (2024). Are Objective Explanatory Evaluation metrics Trustworthy? An Adversarial Analysis. arXiv preprint arXiv:2406.07820. Article Link, Code

3. Yarici, Y., Kokilepersaud, K., Prabhushankar, M., & AlRegib, G. (2024). Explaining Representation Learning with Perceptual Components. arXiv preprint arXiv:2406.06930. Article Link, Code

4. Kokilepersaud, K., Yarici, Y., Prabhushankar, M., & AlRegib, G. (2024). Taxes Are All You Need: Integration of Taxonomical Hierarchy Relationships into the Contrastive Loss. arXiv preprint arXiv:2406.06848. Article Link, Code

5. Prabhushankar, M., & AlRegib, G. (2024). Counterfactual Gradients-based Quantification of Prediction Trust in Neural Networks. arXiv preprint arXiv:2405.13758. Article Link, Code

1. Prabhushankar, M., & AlRegib, G. (2024). VOICE: Variance of Induced Contrastive Explanations to quantify Uncertainty in Neural Network Interpretability. IEEE Journal of Selected Topics in Signal Processing. Article Link, Code

2. Benkert, R., Prabhushankar, M., & AlRegib, G. (2024). Effective Data Selection for Seismic Interpretation through Disagreement. IEEE Transactions on Geoscience and Remote Sensing. Article Link

1. Kokilepersaud, K., Corona, S. T., Prabhushankar, M., AlRegib, G., & Wykoff, C. (2023). Clinically labeled contrastive learning for oct biomarker classification. IEEE Journal of Biomedical and Health Informatics, 27(9), 4397-4408. Article Link, Code

2. Kokilepersaud, K., Prabhushankar, M., Yarici, Y., AlRegib, G., & Parchami, A. (2023). Exploiting the distortion-semantic interaction in fisheye data. IEEE Open Journal of Signal Processing, 4, 284-293. Article Link, Code

3. Lee, J., Lehman, C., Prabhushankar, M., & AlRegib, G. (2023). Probing the purview of neural networks via gradient analysis. IEEE Access, 11, 32716-32732. Article Link

4. Prabhushankar, M., & AlRegib, G. (2023). Stochastic surprisal: An inferential measurement of free energy in neural networks. Frontiers in Neuroscience, 17, 926418. Article Link, Code

5. Benkert, R., Prabhushankar, M., AlRegib, G., Pacharmi, A., & Corona, E. (2023). Gaussian Switch Sampling: A Second-Order Approach to Active Learning. IEEE Transactions on Artificial Intelligence, 5(1), 38-50. Article Link

1. AlRegib, G., & Prabhushankar, M. (2022). Explanatory paradigms in neural networks: Towards relevant and contextual explanations. IEEE Signal Processing Magazine, 39(4), 59-72. Article Link, Code

1. Temel, D., Prabhushankar, M., & AlRegib, G. (2016). UNIQUE: Unsupervised image quality estimation. IEEE signal processing letters, 23(10), 1414-1418. Article Link, Code

1. Benkert, R., Prabhushankar, M., & AlRegib, G. Transitional Uncertainty with Layered Intermediate Predictions. In Forty-first International Conference on Machine Learning. Article Link

2. Schneider, J., & Prabhushankar, M. (2024, March). Understanding and Leveraging the Learning Phases of Neural Networks. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 38, No. 13, pp. 14886-14893). Article Link.

3. Quesada, J., Alotaibi, M., Prabhushankar, M., & Alregib, G. (2024). PointPrompt: A Multi-modal Prompting Dataset for Segment Anything Model. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 1604-1610). Article Link, Code, Dataset

1. Kokilepersaud, K., Logan, Y.Y., Benkert, R., Zhou, C., Prabhushankar, M., AlRegib, G., Corona, E., Singh, K. and Parchami, M., 2023, December. FOCAL: A Cost-Aware Video Dataset for Active Learning. In 2023 IEEE International Conference on Big Data (BigData) (pp. 1269-1278). IEEE. Article Link, Code, Dataset

2. Fowler, Z., Kokilepersaud, K. P., Prabhushankar, M., & AlRegib, G. (2023, September). Clinical trial active learning. In Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (pp. 1-10). Article Link, Code

3. Chowdhury, P., Mustafa, A., Prabhushankar, M., & AlRegib, G. (2023, August). Counterfactual uncertainty for high dimensional tabular dataset. In SEG International Exposition and Annual Meeting (pp. SEG-2023). SEG. Article Link

4. Zhou, C., Prabhushankar, M., & AlRegib, G. (2023, August). Perceptual quality-based model training under annotator label uncertainty. In SEG International Exposition and Annual Meeting (pp. SEG-2023). SEG. Article Link, Code

5. Benkert, R., Prabhushankar, M., & AlRegib, G. (2023, August). What samples must seismic interpreters label for efficient machine learning?. In Third International Meeting for Applied Geoscience & Energy (pp. 1004-1009). Society of Exploration Geophysicists and American Association of Petroleum Geologists. Article Link.

6. Chowdhury, P., Prabhushankar, M., & AlRegib, G. (2023). Explaining explainers: Necessity and sufficiency in tabular data. In NeurIPS 2023 Second Table Representation Learning Workshop. Article Link

1. Prabhushankar, M., Kokilepersaud, K., Logan, Y. Y., Trejo Corona, S., AlRegib, G., & Wykoff, C. (2022). Olives dataset: Ophthalmic labels for investigating visual eye semantics. Advances in Neural Information Processing Systems, 35, 9201-9216. Article Link, Code, Dataset

2. Prabhushankar, M., & AlRegib, G. (2022). Introspective learning: A two-stage approach for inference in neural networks. Advances in Neural Information Processing Systems, 35, 12126-12140. Article Link, Code

3. C. Zhou, M. Prabhushankar, and G. AlRegib, "On the Ramifications of Human Label Uncertainty," in NeurIPS 2022 Workshop on Human in the Loop Learning, New Orleans, LA, Dec. 2 2022. Article Link, Code

4. K. Kokilepersaud, M. Prabhushankar, and G. AlRegib, "Clinical Contrastive Learning for Biomarker Detection," in NeurIPS 2022 Workshop: Self-Supervised Learning - Theory and Practice, New Orleans, LA, Nov. 28 - Dec. 9 2022. Article Link, Code

5. Benkert, R., Prabhushankar, M., & AlRegib, G. (2022, October). Forgetful active learning with switch events: Efficient sampling for out-of-distribution data. In 2022 IEEE International Conference on Image Processing (ICIP) (pp. 2196-2200). IEEE. Article Link

6. Kokilepersaud, K., Prabhushankar, M., AlRegib, G., Corona, S. T., & Wykoff, C. (2022, October). Gradient-based severity labeling for biomarker classification in oct. In 2022 IEEE International Conference on Image Processing (ICIP) (pp. 3416-3420). IEEE. Article Link

7. Kokilepersaud, K., Prabhushankar, M., & AlRegib, G. (2022, August). Volumetric supervised contrastive learning for seismic semantic segmentation. In Second International Meeting for Applied Geoscience & Energy (pp. 1699-1703). Society of Exploration Geophysicists and American Association of Petroleum Geologists. Article Link

8. Benkert, R., Prabhushankar, M., & AlRegib, G. (2022, August). Reliable uncertainty estimation for seismic interpretation with prediction switches. In Second International Meeting for Applied Geoscience & Energy (pp. 1740-1744). Society of Exploration Geophysicists and American Association of Petroleum Geologists. Artcle Link

9. Y. Logan, M. Prabhushankar and G. AlRegib, ”DECAL: DEployable Clinical Active Learning,” ICML 2022 Workshop on Adaptive Experimental Design and Active Learning in the Real World, July 2022. Article Link, Code

10. J. Lee, M. Prabhushankar, and G. AlRegib, “Gradient-Based Adversarial and Outof-Distribution Detection,” in International Conference on Machine Learning (ICML) Workshop on New Frontiers in Adversarial Machine Learning, Baltimore, MD, USA, July 2022. Article Link

1. Prabhushankar, M., & AlRegib, G. (2021, September). Extracting causal visual features for limited label classification. In 2021 IEEE International Conference on Image Processing (ICIP) (pp. 3697-3701). IEEE. Article Link

1. Prabhushankar, M., Kwon, G., Temel, D., & AlRegib, G. (2020, October). Contrastive explanations in neural networks. In 2020 IEEE International Conference on Image Processing (ICIP) (pp. 3289-3293). IEEE. Article Link, Code

2. Kwon, G., Prabhushankar, M., Temel, D., & AlRegib, G. (2020, October). Novelty detection through model-based characterization of neural networks. In 2020 IEEE International Conference on Image Processing (ICIP) (pp. 3179-3183). IEEE. Article Link, Code

3. Sun, Y., Prabhushankar, M., & AlRegib, G. (2020, October). Implicit saliency in deep neural networks. In 2020 IEEE International Conference on Image Processing (ICIP) (pp. 2915-2919). IEEE. Article Link, Code

4. Kwon, G., Prabhushankar, M., Temel, D., & AlRegib, G. (2020). Backpropagated gradient representations for anomaly detection. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXI 16 (pp. 206-226). Springer International Publishing. Article Link, Code

1. Kwon, G., Prabhushankar, M., Temel, D., & AlRegib, G. (2019, September). Distorted representation space characterization through backpropagated gradients. In 2019 IEEE International Conference on Image Processing (ICIP) (pp. 2651-2655). IEEE. Article Link, Code

1. Shafiq, M. A., Prabhushankar, M., Di, H., & AlRegib, G. (2018). Towards understanding common features between natural and seismic images. In SEG Technical Program Expanded Abstracts 2018 (pp. 2076-2080). Society of Exploration Geophysicists. Article Link

2. Prabhushankar, M., Kwon, G., Temel, D., & AIRegib, G. (2018, October). Semantically interpretable and controllable filter sets. In 2018 25th IEEE International Conference on Image Processing (ICIP) (pp. 1053-1057). IEEE. Article Link

3. Shafiq, M. A., Prabhushankar, M., & AlRegib, G. (2018, June). Leveraging sparse features learned from natural images for seismic understanding. In 80th EAGE Conference and Exhibition 2018 (Vol. 2018, No. 1, pp. 1-5). European Association of Geoscientists & Engineers. Article Link

4. Shafiq, M. A., Prabhushankar, M., Long, Z., Di, H., & Alregib, G. Attention Models Based on Sparse Autoencoders for Seismic Interpretation. In AAPG ACE 2018. Presentation Link

1. D. Temel, G. Kwon*, M. Prabhushankar*, and G. AlRegib, “CURE-TSR: Challenging unreal and real environments for traffic sign recognition,” in Neural Information Processing Systems (NIPS) Workshop on Machine Learning for Intelligent Transportation Systems (MLITS), Long Beach, U.S., December 2017. (*: equal contribution). Article Link, Code/Dataset

2. Prabhushankar, M., Temel, D., & AlRegib, G. (2017). MS-UNIQUE: Multi-model and Sharpness-weighted Unsupervised Image Quality Estimation. Electronic Imaging, 29, 30-35. Article Link, Code

3. Prabhushankar, M., Temel, D., & AlRegib, G. (2017, September). Generating adaptive and robust filter sets using an unsupervised learning framework. In 2017 IEEE International Conference on Image Processing (ICIP) (pp. 3041-3045). IEEE. Article Link

1. Parchami, Mostafa, Enrique Corona, Ghassan AlRegib, Mohit Prabhushankar, and Ryan Benkert. "Neural network training." U.S. Patent 12,020,475, issued June 25, 2024. Patent Link.

2. AlRegib, Ghassan, Kiran Kokilepersaud, Mohit Prabhushankar, Yash-yee Logan, and Ahmad Mustafa. "Asymmetric Multi-Modal Machine Learning System and Method using Clinical Metadata in Electronic Medical Records." U.S. Patent Application 18/514,542, filed May 23, 2024. Patent Link.

3. AlRegib, Ghassan, Kiran Kokilepersaud, and Mohit Prabhushankar. "Image-Based Severity Detection Method and System." U.S. Patent Application No. 18/513,805. Patent Link.

1. AlRegib, G., Kwon, G., Prabhushankar, M. and Temel, D., Georgia Tech Research Corp, 2022. Detecting and Classifying Anomalies in Artificial Intelligence Systems. U.S. Patent Application 17/633,878. Patent Link

2. Parchami, A., AlRegib, G., Temel, D., Prabhushankar, M. and Kwon, G., Ford Global Technologies LLC, 2022. Variance of gradient based active learning framework for training perception algorithms. U.S. Patent Application 17/172,854. Patent Link

1. Amico, Andrea, and Mohit Prabhushankar. "System, method, and apparatus for detection of damages on surfaces." U.S. Patent 10,255,521, issued April 9, 2019. Patent Link

1. Amico, Andrea, and Mohit Prabhushankar. "Artificial intelligence based vehicle dashboard analysis." U.S. Patent 10,152,641, issued December 11, 2018. Patent Link

Prabhushankar, M. (2021). Contrastive Reasoning in Neural Networks. Link