no code implementations • 17 Feb 2024 • Zhenghang Yuan, Zhitong Xiong, Lichao Mou, Xiao Xiang Zhu
In this context, we introduce a global-scale, high-quality image-text dataset for remote sensing, providing natural language descriptions for Sentinel-2 data to facilitate the understanding of satellite imagery for common users.
no code implementations • 7 Jul 2023 • Konrad Heidler, Lichao Mou, Erik Loebel, Mirko Scheinert, Sébastien Lefèvre, Xiao Xiang Zhu
Building on this observation, we completely rephrase the task as a contour tracing problem and propose a model for explicit contour detection that does not incorporate any dense predictions as intermediate steps.
no code implementations • 14 Jun 2023 • Zhenghang Yuan, Lichao Mou, Yuansheng Hua, Xiao Xiang Zhu
Localizing desired objects from remote sensing images is of great use in practical applications.
no code implementations • 1 Jun 2023 • Zhenghang Yuan, Lichao Mou, Xiao Xiang Zhu
Based on the adversarial branch, we introduce two regularizers to constrain the training process against language bias.
1 code implementation • 24 May 2023 • Zhitong Xiong, Sining Chen, Yi Wang, Lichao Mou, Xiao Xiang Zhu
Towards a fair and comprehensive analysis of existing methods, the proposed benchmark consists of 1) a large-scale dataset including co-registered RGB and nDSM pairs and pixel-wise semantic labels; 2) a comprehensive evaluation and analysis of existing multi-modal fusion strategies for both convolutional and Transformer-based networks on remote sensing data.
Ranked #1 on Semantic Segmentation on GAMUS
no code implementations • 7 Apr 2023 • Zhenghang Yuan, Lichao Mou, Xiao Xiang Zhu
With the proposed augmented dataset, we are able to obtain more questions in addition to the original ones with the same meaning.
no code implementations • ICCV 2023 • Runmin Dong, Lichao Mou, Mengxuan Chen, Weijia Li, Xin-Yi Tong, Shuai Yuan, Lixian Zhang, Juepeng Zheng, Xiaoxiang Zhu, Haohuan Fu
Moreover, we propose the Class Center Contrast method to jointly utilize the labeled and unlabeled data.
1 code implementation • 25 Sep 2022 • Pu Jin, Lichao Mou, Gui-Song Xia, Xiao Xiang Zhu
In this paper, we create a new dataset, named DroneAnomaly, for anomaly detection in aerial videos.
no code implementations • 22 Sep 2022 • Pu Jin, Lichao Mou, Yuansheng Hua, Gui-Song Xia, Xiao Xiang Zhu
Furthermore, the holistic features are refined by the multi-scale temporal relations in a novel fusion module for yielding more discriminative video representations.
2 code implementations • 27 Jun 2022 • Yi Wang, Conrad M Albrecht, Nassim Ait Ali Braham, Lichao Mou, Xiao Xiang Zhu
In deep learning research, self-supervised learning (SSL) has received great attention triggering interest within both the computer vision and remote sensing communities.
Ranked #3 on Multi-Label Image Classification on BigEarthNet
no code implementations • 24 Jun 2022 • Nassim Ait Ali Braham, Lichao Mou, Jocelyn Chanussot, Julien Mairal, Xiao Xiang Zhu
Deep learning has proven to be a very effective approach for Hyperspectral Image (HSI) classification.
no code implementations • 6 May 2022 • Zhenghang Yuan, Lichao Mou, Qi Wang, Xiao Xiang Zhu
To be more specific, a language-guided SPCL method with a soft weighting strategy is explored in this work.
1 code implementation • 12 Dec 2021 • Zhenghang Yuan, Lichao Mou, Zhitong Xiong, Xiaoxiang Zhu
In order to provide every user with flexible access to change information and help them better understand land-cover changes, we introduce a novel task: change detection-based visual question answering (CDVQA) on multi-temporal aerial images.
no code implementations • 18 Nov 2021 • Yao Sun, Lichao Mou, Yuanyuan Wang, Sina Montazeri, Xiao Xiang Zhu
Building height retrieval from synthetic aperture radar (SAR) imagery is of great importance for urban applications, yet highly challenging owing to the complexity of SAR data.
1 code implementation • 15 Aug 2021 • Tianze Yu, Jianzhe Lin, Lichao Mou, Yuansheng Hua, Xiaoxiang Zhu, Z. Jane Wang
In our experiments, trained with single-labeled MAI-AID-s and MAI-UCM-s datasets, the proposed model is tested directly on our collected Multi-scene Aerial Image (MAI) dataset.
1 code implementation • 13 Aug 2021 • Lei Ding, Haitao Guo, Sicong Liu, Lichao Mou, Jing Zhang, Lorenzo Bruzzone
Recent studies indicate that the SCD can be modeled through a triple-branch Convolutional Neural Network (CNN), which contains two temporal branches and a change branch.
1 code implementation • 2 Aug 2021 • Konrad Heidler, Lichao Mou, Di Hu, Pu Jin, Guangyao Li, Chuang Gan, Ji-Rong Wen, Xiao Xiang Zhu
By fine-tuning the models on a number of commonly used remote sensing datasets, we show that our approach outperforms existing pre-training strategies for remote sensing imagery.
Ranked #2 on Cross-Modal Retrieval on SoundingEarth
no code implementations • 9 Jul 2021 • Sudipan Saha, Lichao Mou, Muhammad Shahzad, Xiao Xiang Zhu
The proposed method exploits this property to sample smaller patches from the larger scene and uses deep clustering and contrastive learning to refine the weights of a lightweight deep model composed of a series of the convolution layers along with an embedded channel attention.
1 code implementation • 29 Apr 2021 • Jun Li, Zhaocong Wu, Zhongwen Hu, Canliang Jian, Shaojie Luo, Lichao Mou, Xiao Xiang Zhu, Matthieu Molinier
In the encoder, three input branches are designed to handle spectral bands at their native resolution and extract multiscale spectral features.
1 code implementation • 7 Apr 2021 • Yuansheng Hua, Lichao Mou, Pu Jin, Xiao Xiang Zhu
We conduct experiments with extensive baseline models on both MultiScene-Clean and MultiScene to offer benchmarks for multi-scene recognition in single images and learning from noisy labels for this task, respectively.
1 code implementation • 15 Mar 2021 • Lichao Mou, Sudipan Saha, Yuansheng Hua, Francesca Bovolo, Lorenzo Bruzzone, Xiao Xiang Zhu
To this end, we frame the problem of unsupervised band selection as a Markov decision process, propose an effective method to parameterize it, and finally solve the problem by deep reinforcement learning.
5 code implementations • 2 Mar 2021 • Konrad Heidler, Lichao Mou, Celia Baumhoer, Andreas Dietz, Xiao Xiang Zhu
Deep learning-based coastline detection algorithms have begun to outshine traditional statistical methods in recent years.
1 code implementation • 10 Jan 2021 • Yuansheng Hua, Diego Marcos, Lichao Mou, Xiao Xiang Zhu, Devis Tuia
Training Convolutional Neural Networks (CNNs) for very high resolution images requires a large quantity of high-quality pixel-level annotations, which is extremely labor- and time-consuming to produce.
no code implementations • 17 Nov 2020 • Yao Sun, Yuansheng Hua, Lichao Mou, Xiao Xiang Zhu
Object retrieval and reconstruction from very high resolution (VHR) synthetic aperture radar (SAR) images are of great importance for urban SAR applications, yet highly challenging owing to the complexity of SAR data.
no code implementations • 17 Jun 2020 • Xiao Xiang Zhu, Sina Montazeri, Mohsin Ali, Yuansheng Hua, Yuanyuan Wang, Lichao Mou, Yilei Shi, Feng Xu, Richard Bamler
Deep learning in remote sensing has become an international hype, but it is mostly limited to the evaluation of optical data.
no code implementations • 6 Jun 2020 • Qingyu Li, Lichao Mou, Yuansheng Hua, Yao Sun, Pu Jin, Yilei Shi, Xiao Xiang Zhu
The detected keypoints are subsequently reformulated as a closed polygon, which is the semantic boundary of the building.
1 code implementation • ECCV 2020 • Di Hu, Xuhong LI, Lichao Mou, Pu Jin, Dong Chen, Liping Jing, Xiaoxiang Zhu, Dejing Dou
With the help of this dataset, we evaluate three proposed approaches for transferring the sound event knowledge to the aerial scene recognition task in a multimodal learning framework, and show the benefit of exploiting the audio information for the aerial scene recognition.
1 code implementation • 14 May 2020 • Di Hu, Lichao Mou, Qingzhong Wang, Junyu. Gao, Yuansheng Hua, Dejing Dou, Xiao Xiang Zhu
Visual crowd counting has been recently studied as a way to enable people counting in crowd scenes from images.
no code implementations • 30 Jan 2020 • Lichao Mou, Yuansheng Hua, Pu Jin, Xiao Xiang Zhu
In this paper, we introduce a novel problem of event recognition in unconstrained aerial videos in the remote sensing community and present a large-scale, human-annotated dataset, named ERA (Event Recognition in Aerial videos), consisting of 2, 864 videos each with a label from 25 different classes corresponding to an event unfolding 5 seconds.
1 code implementation • 19 Dec 2019 • Xiao Xiang Zhu, Jingliang Hu, Chunping Qiu, Yilei Shi, Jian Kang, Lichao Mou, Hossein Bagheri, Matthias Häberle, Yuansheng Hua, Rong Huang, Lloyd Hughes, Hao Li, Yao Sun, Guichen Zhang, Shiyao Han, Michael Schmitt, Yuanyuan Wang
This is especially true for an automated analysis of remote sensing images on a global scale, which enables us to address global challenges such as urbanization and climate change using state-of-the-art machine learning techniques.
BIG-bench Machine Learning Cultural Vocal Bursts Intensity Prediction +1
1 code implementation • 16 Jul 2019 • Yuansheng Hua, Lichao Mou, Xiao Xiang Zhu
Particularly, our network consists of three elemental modules: 1) a label-wise feature parcel learning module, 2) an attentional region extraction module, and 3) a label relational inference module.
no code implementations • CVPR 2019 • Lichao Mou, Yuansheng Hua, Xiao Xiang Zhu
Most current semantic segmentation approaches fall back on deep convolutional neural networks (CNNs).
no code implementations • 16 Aug 2018 • Qingpeng Li, Lichao Mou, Qizhi Xu, Yun Zhang, Xiao Xiang Zhu
In this paper, we propose a novel deep network, called rotatable region-based residual network (R$^3$-Net), to detect multi-oriented vehicles in aerial images and videos.
no code implementations • 30 Jul 2018 • Yuansheng Hua, Lichao Mou, Xiao Xiang Zhu
The proposed network consists of three indispensable components: 1) a feature extraction module, 2) a class attention learning layer, and 3) a bidirectional LSTM-based sub-network.
no code implementations • 26 May 2018 • Lichao Mou, Xiao Xiang Zhu
We propose to tackle this problem with a semantic boundary-aware multi-task learning network.
no code implementations • 5 May 2018 • Lichao Mou, Xiao Xiang Zhu
The former is a classification CNN architecture for feature extraction, which takes an input image and produces multi-level convolutional feature maps from shallow to deep; while in the later, to achieve accurate boundary inference and semantic segmentation, boundary-aware high resolution feature maps in shallower layers and high-level but low-resolution features are recursively embedded into the learning framework (from deep to shallow) to generate a fused feature representation that draws a holistic picture of not only high-level semantic information but also low-level fine-grained details.
no code implementations • 7 Mar 2018 • Lichao Mou, Lorenzo Bruzzone, Xiao Xiang Zhu
As far as we know, this is the first time that a recurrent convolutional network architecture has been proposed for multitemporal remote sensing image analysis.
1 code implementation • 28 Feb 2018 • Lichao Mou, Xiao Xiang Zhu
In this paper we tackle a very novel problem, namely height estimation from a single monocular remote sensing image, which is inherently ambiguous, and a technically ill-posed problem, with a large source of uncertainty coming from the overall scale.
no code implementations • 25 Jan 2018 • Lloyd H. Hughes, Michael Schmitt, Lichao Mou, Yuanyuan Wang, Xiao Xiang Zhu
In this letter, we propose a pseudo-siamese convolutional neural network (CNN) architecture that enables to solve the task of identifying corresponding patches in very-high-resolution (VHR) optical and synthetic aperture radar (SAR) remote sensing imagery.
1 code implementation • 11 Oct 2017 • Xiao Xiang Zhu, Devis Tuia, Lichao Mou, Gui-Song Xia, Liangpei Zhang, Feng Xu, Friedrich Fraundorfer
In this article, we analyze the challenges of using deep learning for remote sensing data analysis, review the recent advances, and provide resources to make deep learning in remote sensing ridiculously simple to start with.