Xiaonan Lu

Xiaonan Lu

Auto-generated profile, based on publicly available information

Xiaonan Lu

Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 July 2022 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
XSXian Sun
Xian Sun
PWPeijin Wang
Peijin Wang
WLWanxuan Lu
Wanxuan Lu
ZZZicong Zhu
Zicong Zhu
XLXiaonan Lu
Xiaonan Lu
KFKun Fu
Kun Fu
Deep learning approaches have contributed to the rapid development of Remote Sensing (RS) image interpretation. The most widely used training paradigm is to utilize ImageNet pre-trained models to process RS data for specified tasks. However, there are issues such as domain gap between natural and RS scenes, and the poor generalization capacity of RS models. It makes sense to develop a foundation model with general RS feature representation. Since a large amount of unlabeled data is available, the self-supervised method has more development significance than the fully supervised method in remote sensing. However, most of the current self-supervised methods use contrastive learning, whose performance is sensitive to data augmentation, additional information, and selection of positive and negative pairs. In this paper, we leverage the benefits of generative self-supervised learning for RS images, and propose a Remote sensing foundation Model framework called RingMo, which consists of two parts. First, a large-scale dataset is constructed by collecting two million RS images from satellite and aerial platforms, covering multiple scenes and objects around the world. Second, we propose an RS foundation model training method designed for dense and small objects in complicated RS scenes. We show that the foundation model trained on our dataset with RingMo method achieves state-of-the-art on eight datasets across four downstream tasks, demonstrating the effectiveness of the proposed framework. Through in-depth exploration, we believe it is time for RS researchers to embrace generative self-supervised learning and leverage its general representation capabilities to speed up the development of RS applications.

26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
XLXiaonan Lu
Xiaonan Lu
WDWenhui Diao
Wenhui Diao
Yong-Qiang MaoYong-Qiang Mao
Yong-Qiang Mao
JLJunxi Li
Junxi Li
PWPeijin Wang
Peijin Wang
KFKun Fu
Kun Fu
Few-shot object detection, expecting detectors to detect novel classes with a few instances, has made conspicuous progress. However, the prototypes extracted by existing meta-learning based methods still suffer from insufficient representative information and lack awareness of query images, which cannot be adaptively tailored to different query images. Firstly, only the support images are involved for extracting prototypes, resulting in scarce perceptual information of query images. Secondly, all pixels of all support images are treated equally when aggregating features into prototype vectors, thus the salient objects are overwhelmed by the cluttered background. In this paper, we propose an Information-Coupled Prototype Elaboration (ICPE) method to generate specific and representative prototypes for each query image. Concretely, a conditional information coupling module is introduced to couple information from the query branch to the support branch, strengthening the query-perceptual information in support features. Besides, we design a prototype dynamic aggregation module that dynamically adjusts intra-image and inter-image aggregation weights to highlight the salient information useful for detecting query images. Experimental results on both Pascal VOC and MS COCO demonstrate that our method achieves state-of-the-art performance in almost all settings. Code will be available at: https://github.com/lxn96/ICPE.

28 February 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
XLXiaonan Lu
Xiaonan Lu
XSXian Sun
Xian Sun
WDWenhui Diao
Wenhui Diao
Yong-Qiang MaoYong-Qiang Mao
Yong-Qiang Mao
Junxi LiJunxi Li
Junxi Li
KFKun Fu
Kun Fu
Few-shot object detection (FSOD) has received numerous attention due to the difficulty and time-consuming of labeling objects. Recent researches achieve excellent performance in a natural scene by only using a few instances of novel classes to fine-tune the last prediction layer of the model well-trained on plentiful base data. However, compared with natural scene objects with a single direction and small size variety, the direction and size of the objects in remote sensing images (RSIs) vary greatly. The methods proposed for the natural scene cannot be directly applied to RSIs. In this article, we first propose a strong baseline for RSIs. It fine-tunes all detector components acting on high-level features and effectively improves the performance of novel classes. Further analyzing the results of the baseline, we find that the error for novel classes is mainly concentrated in classification. It misclassifies novel classes as confusable base classes or backgrounds due to the difficulty in extracting generalized information from limited instances. As is well-known, text-modal knowledge can highly summarize the generalized and unique characteristics of categories. Thus, we introduce text-modal descriptions for each category and propose an FSOD method guided by TExt-MOdal knowledge, called TEMO. Specifically, a text-modal knowledge extractor and a cross-modal assembly module are proposed to extract text features and fuse the text-modal features into visual-modal features. The fused features greatly reduce the classification confusion of novel classes. Furthermore, we introduce a mask strategy and a separation loss to avoid over-fitting and ambiguity of text-modal features. Experimental results on detection in optical remote sensing images (DIOR), Northwestern Polytechnical University (NWPU), and fine-grained object recognition in high-resolution remote sensing imagery (FAIR1M) illustrate that our TEMO achieves state-of-the-art performance in all settings.

13 August 2021 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
XLXiaonan Lu
Xiaonan Lu
XSXian Sun
Xian Sun
WDWenhui Diao
Wenhui Diao
YFYingchao Feng
Yingchao Feng
PWPeijin Wang
Peijin Wang
KFKun Fu
Kun Fu
Existing deep learning models usually assume that all data obeys independent identically distribution, which is unreasonable in remote sensing. Due to the differences in camera parameters, spectral ranges, resolutions, and so on, the images acquired by remote sensing sensors may be greatly diverse, causing models to face catastrophic forgetting when they are trained on new data only. Thus, incremental learning is introduced. An ideal incremental learning model should be expanded as the number of tasks increases, so as to have enough ability to adapt to the changes in data. However, existing approaches normally expand heavy modules for each task, making the holistic models cumbersome. In this article, a lightweight incremental learning approach (LIL) is proposed for remote sensing image scene classification. We replace the role of the feature extractor with extracting features of a single task instead of task-sharing features of all tasks to lighten the backbone. In addition, we propose a light feature transfer module (FTM) to realize the alignment of data distributions between different tasks in the feature domain. Furthermore, dual-constraint loss with knowledge distillation and adversarial learning is introduced to promote the mapping and alignment of data distributions at both the feature level and the semantic level. In LIL, only a tiny FTM and a classifier are added to the model when the model learns a new task. Experimental results show that our approach with a small number of parameters outperforms state-of-the-art approaches for incremental learning on both a single dataset and a sequence of multiple datasets.

29 October 2021 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
Junxi LiJunxi Li
Junxi Li
XSXian Sun
Xian Sun
WDWenhui Diao
Wenhui Diao
PWPeijin Wang
Peijin Wang
YFYingchao Feng
Yingchao Feng
GXGuangluan Xu
Guangluan Xu
Due to the differences in the feature distribution between classes, when the model learns in a continuous data stream, it will encounter catastrophic forgetting. The incremental learning methods have shown great potential to solve this problem. However, most existing methods based on task-incremental learning are difficult to adapt to characteristics of remote sensing scenes with few differences in appearance but large differences in features, which is not conducive to artificially distinguish task-identity document (ID). Thus, we propose a class-incremental learning (CIL) network for small objects enhancing semantic segmentation in aerial imagery. Specifically, considering the superior accuracy of the binary classifier, we propose a twin-auxiliary (TA) model that adds an auxiliary binary classification task. Then, for expansion and contraction at the edge and small object confusion problems, we introduce a diversity distillation loss, using the results of binary-classifier to constrain the multiclass segmentation results and strengthen the attention to the locations of the segmentation results that have changed. Finally, we design a conflict reduction mechanism for multihead classifier to achieve single-head prediction for CIL. Experiments demonstrate that our method has good performance on the Vaihingen and Potsdam datasets by the International Society for Photogrammetry and Remote Sensing (ISPRS), outperforming state-of-the-art (SOTA) incremental learning methods. The code will be available soon.

24 August 2021 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
XSXian Sun
Xian Sun
PWPeijin Wang
Peijin Wang
ZYZhiyuan Yan
Zhiyuan Yan
WDWenhui Diao
Wenhui Diao
XLXiaonan Lu
Xiaonan Lu
KFKun Fu
Kun Fu
In this article, we introduce the 2020 Gaofen Challenge and relevant scientific outcomes. The 2020 Gaofen Challenge is an international competition, which is organized by the China High-Resolution Earth Observation Conference Committee and the Aerospace Information Research Institute, Chinese Academy of Sciences and technically cosponsored by the IEEE Geoscience and Remote Sensing Society and the International Society for Photogrammetry and Remote Sensing. It aims at promoting the academic development of automated high-resolution earth observation image interpretation. Six independent tracks have been organized in this challenge, which cover the challenging problems in the field of object detection and semantic segmentation. With the development of convolutional neural networks, deep-learning-based methods have achieved good performance on image interpretation. In this article, we report the details and the best-performing methods presented so far in the scope of this challenge.