“Robust Object Detection Under Dataset Shifts,” a Presentation from Arm

Partha Maji, Principal Research Scientist at Arm’s Machine Learning Research Lab, presents the “Robust Object Detection Under Dataset Shifts” tutorial at the May 2021 Embedded Vision Summit.

In image classification tasks, the evaluation of models’ robustness to increased dataset shifts with a probabilistic framework is very well studied. However, object detection (OD) tasks pose other challenges for uncertainty estimation and evaluation. For example, one needs to evaluate both the quality of the label uncertainty (i.e., what?) and spatial uncertainty (i.e., where?) for a given bounding box, but that evaluation cannot be performed with more traditional average precision metrics (e.g., mAP).

In this talk, Maji discusses how to adapt well-established object detection models to generate uncertainty estimations by introducing stochasticity in the form of Monte Carlo Dropout (MC-Drop). He also discusses how such techniques could be extended to a broad class of embedded vision tasks to improve robustness.

See here for a PDF of the slides.

Here you’ll find a wealth of practical technical insights and expert advice to help you bring AI and visual intelligence into your products without flying blind.

Contact

Address

Berkeley Design Technology, Inc.
PO Box #4446
Walnut Creek, CA 94596

Phone
Phone: +1 (925) 954-1411
Scroll to Top