https://scholars.lib.ntu.edu.tw/handle/123456789/636202
標題: | Multidomain Object Detection Framework Using Feature Domain Knowledge Distillation | 作者: | Jaw, Da Wei Huang, Shih Chia Lu, Zhi Hui Fung, Benjamin C.M. SY-YEN KUO |
關鍵字: | Computational complexity | Feature extraction | Generative adversarial networks (GANs) | Knowledge engineering | object detection | Object detection | Task analysis | Testing | Training | unsupervised knowledge distillation (KD) | 公開日期: | 1-一月-2023 | 卷: | PP | 來源出版物: | IEEE Transactions on Cybernetics | 摘要: | Object detection techniques have been widely studied, utilized in various works, and have exhibited robust performance on images with sufficient luminance. However, these approaches typically struggle to extract valuable features from low-luminance images, which often exhibit blurriness and dim appearence, leading to detection failures. To overcome this issue, we introduce an innovative unsupervised feature domain knowledge distillation (KD) framework. The proposed framework enhances the generalization capability of neural networks across both low-and high-luminance domains without incurring additional computational costs during testing. This improvement is made possible through the integration of generative adversarial networks and our proposed unsupervised KD process. Furthermore, we introduce a region-based multiscale discriminator designed to discern feature domain discrepancies at the object level rather than from the global context. This bolsters the joint learning process of object detection and feature domain distillation tasks. Both qualitative and quantitative assessments shown that the proposed method, empowered by the region-based multiscale discriminator and the unsupervised feature domain distillation process, can effectively extract beneficial features from low-luminance images, outperforming other state-of-the-art approaches in both low-and sufficient-luminance domains. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/636202 | ISSN: | 21682267 | DOI: | 10.1109/TCYB.2023.3300963 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。