计算机科学
地理空间分析
卷积神经网络
视觉对象识别的认知神经科学
对象(语法)
人工智能
滤波器(信号处理)
蒸馏
特征(语言学)
深度学习
人工神经网络
特征提取
任务(项目管理)
模式识别(心理学)
计算机视觉
遥感
地质学
工程类
哲学
有机化学
化学
系统工程
语言学
作者
Liuqian Wang,Jing Zhang,Jimiao Tian,Jiafeng Li,Zhuo Li,Qi Tian
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing
[Institute of Electrical and Electronics Engineers]
日期:2023-01-01
卷期号:61: 1-16
标识
DOI:10.1109/tgrs.2023.3260883
摘要
With the development of high-resolution remote sensing images (HR-RSIs) and the escalating demand for intelligent analysis, fine-grained recognition of geospatial objects has become a more practical and challenging task. Although deep learning-based object recognition has achieved superior performance, it is inflexible to be directly utilized to the fine-grained object recognition tasks of HR-RSIs under the limitation of the size of geospatial objects. An efficient fine-grained object recognition method in HR-RSIs from knowledge distillation to filter grafting is proposed. Specifically, fine-grained object recognition consists of two stages: Stage 1 utilizes oriented region convolutional neural network (oriented R-CNN) to accurately locate and preliminarily classify geospatial objects. At the same time, it serves as a teacher network to guide students’ effective learning of fine-grained object recognition; in Stage 2, we design a coarse-to-fine object recognition network (CF-ORNet), as the second teacher network, which realizes fine-grained recognition through feature learning and category correction. After that, we propose a lightweight model from knowledge distillation to filter grafting on two teacher networks to achieve efficient fine-grained object recognition. The experimental results on VEDAI and HRSC2016 datasets achieve competitive performance.
科研通智能强力驱动
Strongly Powered by AbleSci AI