Training vision-based Autonomous driving models is a challenging problem with enormous practical implications. One of the main challenges is the requirement of storage and processing of vast volumes of (possibly redundant) driving video data. In this talk, we discuss the problem of data-efficient training of autonomous driving systems.
1. Multi-criteria online Frame-subset Selection for Autonomous Vehicle Videos Soumi Das, Sayan Mandal, Ashwin Bhoyar, Madhumita Bharde, Niloy Ganguly, Suparna Bhattacharya, and Sourangshu Bhattacharya. Pattern Recognition Letters (2020)
2. Das, Soumi, Harikrishna Patibandla, Suparna Bhattacharya, Kshounis Bera, Niloy Ganguly, and Sourangshu Bhattacharya. "Convex Online Video Frame Subset Selection using Multiple Criteria for Data Efficient Autonomous Driving." arXiv preprint arXiv:2103.13021 (2021).