Can I read RMOPP: Robust Multi-Objective Post-Processing for Effective Object Detection on EtoBox?

RMOPP: Robust Multi-Objective Post-Processing for Effective Object Detection by Savargaonkar, Mayuresh; Chehade, Abdallah; Rawashdeh, Samir is a scholarly article available to read on EtoBox.

What is RMOPP: Robust Multi-Objective Post-Processing for Effective Object Detection about?

Over the last few decades, many architectures have been developed that harness the power of neural networks to detect objects in near real-time. Training such systems requires substantial time across multiple GPUs and massive labeled training datasets. Although the goal of these systems is generalizability, they are often impractical in real-life applications due to flexibility, robustness, or speed issues. This paper proposes RMOPP: A robust multi-objective post-processing algorithm to boost the performance of fast pre-trained object detectors with a negligible impact on their speed. Specifically, RMOPP is a statistically driven, post-processing algorithm that allows for simultaneous optimization of precision and recall. A unique feature of RMOPP is the Pareto frontier that identifies dominant possible post-processed detectors to optimize for both precision and recall. RMOPP explores the full potential of a pre-trained object detector and is deployable for near real-time predictions. We also provide a compelling test case on YOLOv2 using the MS-COCO dataset.

Author

Savargaonkar, Mayuresh; Chehade, Abdallah; Rawashdeh, Samir

Published

2021

Language

EN