An Approach to Incorporating Implicit Knowledge in Object Detection Models
Open Access
- 4 March 2024
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 14 (5) , 2124
Abstract
Current object detection methods typically focus on addressing the distribution discrepancies between source and target domains. However, solely concentrating on this aspect may lead to overlooking the inherent limitations of the samples themselves. This study proposes a method to integrate implicit knowledge into object detection models, aiming to enhance the models’ effectiveness in identifying target features within images. We analyze the sources of information loss in object detection models, treating this loss as a form of implicit knowledge and modeling it in the form of dictionaries. We explore potentially effective ways of integrating latent knowledge into the models and then apply it to object detection models. The models demonstrate a 1% and 0.8% improvement in mean average precision(mAP) in the UA-DETRAC and KITTI datasets, respectively. The results indicate that the proposed method can effectively enhance the relevant metrics of object detection models without significantly increasing the parameter or computational overhead. By excavating and utilizing implicit knowledge, we enhance the performance and efficiency of the models, offering new perspectives and methods for addressing challenges in practical applications.Keywords
This publication has 23 references indexed in Scilit:
- Object Detection in 20 Years: A SurveyProceedings of the IEEE, 2023
- CE-FPN: enhancing channel information for object detectionMultimedia Tools and Applications, 2022
- A Comprehensive Survey on Transfer LearningProceedings of the IEEE, 2021
- UA-DETRAC: A new benchmark and protocol for multi-object detection and trackingComputer Vision and Image Understanding, 2020
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design2018
- CBAM: Convolutional Block Attention Module2018
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- Squeeze-and-Excitation Networks2018
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- A Stochastic Approximation MethodThe Annals of Mathematical Statistics, 1951