TMCOSS: Thresholded Multi-Criteria Online Subset Selection for Data-Efficient Autonomous Driving

Soumi Das, Harikrishna Patibandla, Suparna Bhattacharya, Kshounis Bera, Niloy Ganguly, Sourangshu Bhattacharya; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 6341-6350

Abstract


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 paper, we study the problem of data-efficient training of autonomous driving systems. We argue that in the context of an edge-device deployment, multi-criteria online video frame subset selection is an appropriate technique for developing such frameworks. We study existing convex optimization based solutions and show that they are unable to provide solution with high weightage to loss of selected video frames. We design a novel multi-criteria online subset selection algorithm, TMCOSS, which uses a thresholded concave function of selection variables. Extensive experiments using driving simulator CARLA show that we are able to drop 80% of the frames, while succeeding to complete 100% of the episodes. We also show that TMCOSS improves performance on the crucial affordance 'Relative Angle' during turns, on inclusion of bucket-specific relative angle loss (BL), leading to selection of more frames in those parts. TMCOSS also achieves an 80% reduction in number of training video frames, on real-world videos from the standard BDD and Cityscapes datasets, for the tasks of drivable area segmentation, and semantic segmentation.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Das_2021_ICCV, author = {Das, Soumi and Patibandla, Harikrishna and Bhattacharya, Suparna and Bera, Kshounis and Ganguly, Niloy and Bhattacharya, Sourangshu}, title = {TMCOSS: Thresholded Multi-Criteria Online Subset Selection for Data-Efficient Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {6341-6350} }