ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Meta-cognition-based simple and effective approach to object detection

Kumar, SP and Gautam, C and Sundaram, S (2021) Meta-cognition-based simple and effective approach to object detection. In: 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021, 6 - 11 June 2021, Virtual, Toronto, pp. 3795-3799.

ICASSP_2021.pdf - Published Version

Download (1MB) | Preview
Official URL: https://doi.org/10.1109/ICASSP39728.2021.9414737


Recently, many researchers have attempted to improve deep learning-based object detection models, both in terms of accuracy and operational speeds. However, frequently, there is a trade-off between speed and accuracy of such models, which encumbers their use in practical applications such as autonomous navigation. In this paper, we explore a meta-cognitive learning strategy for object detection to improve generalization ability while at the same time maintaining detection speed. The meta-cognitive method selectively samples the object instances in the training dataset to reduce overfitting. We use YOLO v3 Tiny as a base model for the work and evaluate the performance using the MS COCO dataset. The experimental results indicate an improvement in absolute precision of 2.6 (minimum), and 4.4 (maximum), with no overhead to inference time.

Item Type: Conference Paper
Publication: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Publisher: Institute of Electrical and Electronics Engineers Inc.
Additional Information: The copyright for this article belongs to the Authors.
Keywords: Deep learning; Economic and social effects; Learning systems; Object recognition, Autonomous navigation; Detection speed; Effective approaches; Generalization ability; Meta cognitions; Meta-cognitive learning; Metacognitives; Training dataset, Object detection
Department/Centre: Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering)
Date Deposited: 01 Jun 2023 10:07
Last Modified: 01 Jun 2023 10:07
URI: https://eprints.iisc.ac.in/id/eprint/81735

Actions (login required)

View Item View Item