卷积神经网络
计算机科学
人工智能
撞击坑
深度学习
灰度
模式识别(心理学)
最小边界框
合成数据
比例(比率)
人工神经网络
图像(数学)
地图学
物理
天文
地理
作者
Huan Yang,Xinchao Xu,Youqing Ma,Yaming Xu,Shaochuang Liu
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing
[Institute of Electrical and Electronics Engineers]
日期:2021-11-30
卷期号:60: 1-12
被引量:15
标识
DOI:10.1109/tgrs.2021.3116348
摘要
Currently, deep neural networks have gained impressive performance for object detection when plenty of labeled training data are available. However, a substantial quantity of labeled data is typically rare and time-consuming to obtain in deep space exploration. To possibly alleviate this problem, we use domain adaptation (DA) to effectively detect unannotated real data samples in the crater detection problem with the help of autoannotated synthetic data samples only. Specifically, we present a novel network, namely, CraterDANet, which unifies image- and feature-level adversarial DAs to bridge the domain gap between synthetic and real data. To evaluate our method, we present a new lunar crater dataset that contains nearly 20 000 small-scale craters captured from different Lunar Reconnaissance Orbital (LRO) Narrow Angle Camera (NAC) grayscale images that have large variations in shape, size, overlap, degradation, and illumination conditions. To the best of our knowledge, this is the first lunar crater dataset with diversification of illumination conditions, which provides bounding box annotations. Through experiments, the proposed CraterDANet, which was trained on labeled synthetic data without using any additional real labeled data, achieved an $F1$ -score of 80.27%, which is slightly better than traditional supervised methods trained on real data. Although the performance still falls short of the state-of-the-art Faster R-convolutional neural network (CNN), it achieves an $F1$ -score of +5.98% performance improvement compared with Faster R-CNN trained on synthetic data only. This result demonstrates the effectiveness of the proposed method for reducing the domain gap between synthetic and real data.
科研通智能强力驱动
Strongly Powered by AbleSci AI