Robust Object Detection Under Dataset Shifts


Date:  Tuesday, May 25

Start Time: 1:30 pm

End Time: 2:00 pm

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

Track

Session Speakers

  • Partha Maji is a Principal Research Scientist at Arm’s ML Research Lab based in Cambridge, where he drives the core research in the efficient implementation of probabilistic machine learning on resource-constrained devices. Prior to this, he worked as a Staff SoC Design Engineer at Broadcom Ltd. where he led various front-end and back-end chip design and implementation activities. Partha started his career in the semiconductor industry as a micro-architecture design engineer in the Processor Division at Arm. He also worked in the software industry for a while before embarking into chip design. He has extensive experience with the end-to-end chip design process starting from microarchitecture-level design to physical design through multiple tape-outs of low-power chips using 65, 40, 28 and 22 nm CMOS process technology. He received a PhD in Computer Science from the University of Cambridge and an MSc in System-on-Chip design from the University of Edinburgh.


Share

Robust Object Detection Under Dataset Shifts