Two-Way Assistant: A Knowledge Distillation Object Detection Method for Remote Sensing Images
Xi Yang, Sheng Zhang, Weichao Yang
Abstract
Due to resource constraints on edge devices, lightweight detection models are gaining popularity in remote sensing. However, achieving efficient performance with these models is challenging compared to traditional detection models. Knowledge distillation (KD) is a promising solution to this issue. However, previous KD methods in remote sensing often suffer from background noise and fail to address feature disparities among detectors. To address the above issues, we introduce the Two-Way Assistant (TWA) distillation method for remote sensing object detection. TWA comprises two crucial modules: the Compression Assistant Module (CPAM) and the Multiscale Adaptive Assistant Module (MAAM). CPAM reduces background information and category interference by compressing and redistributing teacher model features to the student model. MAAM enhances feature knowledge through multi-scale fusion, addressing feature disparities. Through extensive experiments conducted on two distinct types of remote sensing datasets, optical LEVIR and SAR SSDD, our TWA demonstrates favourable performance across both single-stage and two-stage detectors. Especially, it achieves a performance of 82.5% (optical LEVIR dataset) and 95.4% (SAR SSDD dataset) in the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">AP</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">50</sub> metric, superior to existing state-of-the-art methods.