判别式
人工智能
计算机科学
目标检测
遥感
遗忘
光学(聚焦)
分类器(UML)
模式识别(心理学)
地理
语言学
光学
物理
哲学
作者
Tianyang Zhang,Xiangrong Zhang,Peng Zhu,Xiuping Jia,Xu Tang,Licheng Jiao
出处
期刊:Isprs Journal of Photogrammetry and Remote Sensing
日期:2023-01-01
卷期号:195: 353-364
被引量:22
标识
DOI:10.1016/j.isprsjprs.2022.12.004
摘要
Recently few-shot object detection (FSOD) in remote sensing images (RSIs) has drawn increasing attention. However, the current FSOD methods in RSIs merely focus on the detection performance of few-shot novel classes while ignoring the severe degradation of the base class performance. Generalized few-shot object detection (G-FSOD) aims to solve the FSOD problem without forgetting previous knowledge. In this paper, we focus on the G-FSOD in RSIs and propose a Generalized Few-Shot Detector (G-FSDet) that can learn novel knowledge without forgetting. Through the comprehensive analysis of each component in the detector, a novel efficient transfer-learning framework is presented as the foundation of our G-FSDet, which is more suitable for FSOD in remote sensing scenes. Considering the greater intra-class diversity and lower inter-class separability of geospatial objects, we design a metric-based discriminative loss to learn a more discriminative classifier in the few-shot fine-tuning stage. Furthermore, a representation compensation module is proposed to alleviate the catastrophic forgetting problem by decoupling the representation learning of previous and novel knowledge. Extensive experiments on DIOR and NWPU VHR-10.v2 datasets demonstrate that our proposed G-FSDet achieves competitive novel class performance with minor degradation in the base class, reaching state-of-the-art overall performance among all few-shot settings. The source code is available at (https://github.com/RSer-XDU/G-FSDet).
科研通智能强力驱动
Strongly Powered by AbleSci AI