publications

2025

1. 

   On Inherent Adversarial Robustness of Active Vision Systems

   Amitangshu Mukherjee, Timur Ibrayev, and Kaushik Roy

   Transactions on Machine Learning Research, 2025

2. 

   From Clutter to Clarity: Visual Recognition through Foveated Object-Centric Learning (FocL)

   Amitangshu Mukherjee, Deepak Ravikumar, and Kaushik Roy

   In NeurIPS 2025 Workshop: Reliable ML from Unreliable Data, 2025

2024

1. 

   Exploring Foveation and Saccade for Improved Weakly-Supervised Localization

   Timur Ibrayev, Manish Nagaraj, Amitangshu Mukherjee, and 1 more author

   In Proceedings of The 2nd Gaze Meets ML workshop, NeurIPS 2023, 2024

2023

1. 

   Encoding Hierarchical Information in Neural Networks Helps in Subpopulation Shift

   Amitangshu Mukherjee, Isha Garg, and Kaushik Roy

   IEEE Transactions on Artificial Intelligence, 2023

2022

1. 

   Generative Semantic Domain Adaptation for Perception in Autonomous Driving

   Amitangshu Mukherjee, Ameya Joshi, Soumik Sarkar, and 1 more author

   In Journal of Big Data Analytics in Transportation, Nature Springer, 2022

2019

1. 

   Attribute-Controlled Traffic Data Augmentation Using Conditional Generative Models

   Amitangshu Mukherjee, Ameya Joshi, Soumik Sarkar, and 1 more author

   In CVPR Workshop on Vision for All Seasons (VAS), 2019

2. 

   Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers

   Ameya Joshi, Amitangshu Mukherjee, Soumik Sarkar, and 1 more author

   IEEE/CVF International Conference on Computer Vision (ICCV), 2019

3. 

   Semantic Domain Adaptation for Deep Classifiers via GAN-based Data Augmentation

   Amitangshu Mukherjee, Ameya Joshi, Soumik Sarkar, and 1 more author

   In Machine Learning for Autonomous Driving, NeurIPS workshop, 2019