Keming Chen

Keming Chen

Auto-generated profile, based on publicly available information

Keming Chen

Chinese Academy of Sciences

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
7 January 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
CHChunlei Huo
Chunlei Huo
KCKeming Chen
Keming Chen
SZShuaihao Zhang
Shuaihao Zhang
ZWZeyu Wang
Zeyu Wang
HYHeyu Yan
Heyu Yan
ZWZihan Wang
Zihan Wang
Most deep-learning-based vision tasks rely heavily on crowd-labeled data, and a deep neural network (DNN) is usually impacted by the laborious and time-consuming labeling paradigm. Recently, foundation models (FMs) have been presented to learn richer features from multi-modal data. Moreover, a single foundation model enables zero-shot predictions on various vision tasks. The above advantages make foundation models better suited for remote sensing images, where image annotations are more sparse. However, the inherent differences between natural images and remote sensing images hinder the applications of the foundation model. In this context, this paper provides a comprehensive review of common foundation models and domain-specific foundation models for remote sensing, and it summarizes the latest advances in vision foundation models, textually prompted foundation models, visually prompted foundation models, and heterogeneous foundation models. Despite the great potential of foundation models for vision tasks, open challenges concerning data, model, and task impact the performance of remote sensing images and make foundation models far from practical applications. To address open challenges and reduce the performance gap between natural images and remote sensing images, this paper discusses open challenges and suggests potential directions for future advancements.

23 May 2022 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
NSNian Shi
Nian Shi
KCKeming Chen
Keming Chen
GZGuangyao Zhou
Guangyao Zhou
In recent days, change detection has become one of the central tasks for remote sensing image analyses. Due to the powerful discriminative abilities, various convolutional based approaches have been applied and shown favorable performance in change detection. However, these approaches either require numerous parameters to obtain refined features or cannot make full use of the global context information, which is crucial for change detection. Motivated by the recently proposed visual transformers, we introduce a divided spatial and temporal context modeling network to tackle such shortcomings, which is tokens-based and passes the global context by well modeled tokens. Specifically, to model the spatial context, we first use a spatial self-attention to make each token implicitly incorporate the spatial information of the corresponding image. Then a followed temporal selfattention is used to model the temporal context. Together with the spatial self-attention, it makes the learned tokens contain the global context and become more representational and suitable for change detection. Finally, a prediction head is used to output change detection results over the token space without additional transformer decoder or skip connections between features and tokens, thus reducing the model parameters and computational costs. Thanks to the superior global context modeling capabilities of the proposed method, we further develop a simplified variant with much smaller parameters but only a slight drop in F1 and IoU scores. Our proposed method has shown competitive performance and surpasses several state-of-the-art methods according to our experiments. Our model and code will be available at https://github.com/shinianzhihou/ChangeDetection.

2 April 2021 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
PJPing Jian
Ping Jian
KCKeming Chen
Keming Chen
WCWei Cheng
Wei Cheng
Currently, most of the supervised change detection approaches require a training data set that contains samples from both the changed and the unchanged data. However, under certain condition, such as natural disaster and military attack, the changed data samples are very few or even not available but the unchanged data are abundant. In this letter, we develop a generative adversarial networks (GANs)-based one-class classification (OCC) technique for time series remote-sensing image change detection. The proposed method is only trained with the unchanged data instead of both the changed and unchanged data. To achieve this purpose, first, spatial-spectral features are extracted from the time series remote-sensing images. Second, a GAN model is trained to detect the changes only with the extracted features of unchanged data. Remarkably, to offset the outlier errors caused by the incomplete supervision information provided by unchanged data alone, changed data, instead of unchanged data, are generated to improve power of discriminator. Finally, testing data are classified by the trained discriminator of GAN to produce a binary change map. Experimental results obtained on two optical time series remote-sensing data sets confirmed the effectiveness of our proposed method.

8 February 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
PJPing Jian
Ping Jian
YOYimin Ou
Yimin Ou
KCKeming Chen
Keming Chen
Deep learning based hyperspectral image (HSI) change detection (CD) has been a research hotspot. However, the high dimensionality and the limited training samples make HSI-CD difficult to implement. Besides, the data uncertainty inherited from HSIs is often neglected. To deal with these issues, this paper presents an uncertainty aware graph self-supervised learning (UA-GSSL) approach for unsupervised HSI-CD, which allows encoding not only the spectral and topological structure attributes but also the data uncertainty into learned feature representation for downstream CD task. Specifically, spectral and spatial correlations in HSIs are firstly characterized via graph model. Then, based on the constructed spectral-spatial graph models, novel node-level and edge-level data augmentations are devised to enrich the contrastive sample pairs. Thirdly, a graph based dual-branch self-supervised learning (SSL) contrastive network is designed to maximize the mutual information between a pair of low-dimensional feature embeddings. Fourthly, a simple but effective uncertainty aware loss function is dedicatedly formed to encourage the reliable features to play the more dominant role in feature representation. Finally, change map is produced using the learned features. Experimental results obtained on four real HSI datasets sufficiently demonstrate that the UA-GSSL achieves remarkable results compared to twelve state-of-the-art (SOTA) methods. The source code of this article can be downloaded from https://github.com/vickyiiiii /UA-GSSL.

30 September 2020 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
XQXu Quanfu
Xu Quanfu
KCKeming Chen
Keming Chen
XSXian Sun
Xian Sun
YZYue Zhang
Yue Zhang
HLHao Li
Hao Li
GXGuangluan Xu
Guangluan Xu
Facing the challenge of small open labeled data sets in remote sensing change detection, this letter proposes a novel supervised change detection method by taking advantages of capsule network which can reach the same performance as traditional convolutional neural networks (CNNs) but with less training data. To achieve this aim, we propose a pseudo-Siamese capsule network which takes both rotational invariance and spatial hierarchies between features into account for aerial images change detection. First, the features of image pairs are extracted by two identical nonshared weights convolutional capsule networks. Second, the extracted features are directly concatenated and sent to another convolutional capsule layer. The change probability map is obtained by calculating the length of the capsule vectors in the final layer. Additionally, to reduce the influence of imbalance samples when we optimize our network, we design a margin-focal loss function to pay more attention to the misclassified samples. Finally, binary change map can be produced by a simple threshold. Experimental results carried out on the SZTAKI AirChange Benchmark Set show that the proposed method achieves comparable and even better results with existing state-of-the-art methods in terms of F-measure.

18 October 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
PJPing Jian
Ping Jian
YOYimin Ou
Yimin Ou
KCKeming Chen
Keming Chen
Deep learning has shown promising performance in the field of hyperspectral image (HSI) change detection (CD). However, most of these methods often focus on local spatial-spectral information but ignore the high-order correlations contained in multitemporal HSIs. To address this issue, this article proposes a hypergraph self-supervised learning (HG-SSL) based joint spectral-spatial-temporal feature representation algorithm (HyperSST) for downstream HSI-CD. Inspired by the process of human brain perception, HyperSST uniformly models the spectral-spatial-temporal correlations in the form of high-order interactions and skillfully exploits the vertex-level, hyperedge-level, and vertex/hyperedge-level inherent structures within the unlabeled multitemporal HSIs. Specifically, two types of hyperedges, spectral-spatial correlation hyperedge and temporal correlation hyperedge, are first formulated to fully exploit the high-order spectral, spatial, and temporal interactions contained in bitemporal images. Second, two SSL strategies namely contrastive spectral-spatial features learning and generative temporal features learning are skillfully designed to exploit the inherent characteristics of hypergraph models and extract discriminative latent feature representations for downstream tasks. The former captures changes in both attribute space and structure space, while the latter apprehends the changes in temporal space. Third, the learned joint spectral-spatial-temporal features provide a comprehensive representation to qualify the changes between multitemporal images. Extensive experiments on four challenging HSI datasets demonstrate the effectiveness of the proposed approach.