no code implementations • COLING (WNUT) 2022 • Samyo Rode-Hasinger, Anna Kruspe, Xiao Xiang Zhu
In recent years, false information such as fake news, rumors and conspiracy theories on many relevant issues in society have proliferated.
1 code implementation • 18 Apr 2024 • Weikang Yu, Xiaokang Zhang, Samiran Das, Xiao Xiang Zhu, Pedram Ghamisi
Change detection (CD) from remote sensing (RS) images using deep learning has been widely investigated in the literature.
2 code implementations • 22 Mar 2024 • Zhitong Xiong, Yi Wang, Fahong Zhang, Adam J. Stewart, Joëlle Hanna, Damian Borth, Ioannis Papoutsis, Bertrand Le Saux, Gustau Camps-Valls, Xiao Xiang Zhu
The development of foundation models has revolutionized our ability to interpret the Earth's surface using satellite observational data.
1 code implementation • 18 Mar 2024 • Qingsong Xu, Yilei Shi, Jonathan Bamber, Chaojun Ouyang, Xiao Xiang Zhu
Large-scale hydrodynamic models generally rely on fixed-resolution spatial grids and model parameters as well as incurring a high computational cost.
no code implementations • 13 Mar 2024 • Shan Zhao, Ioannis Prapas, Ilektra Karasante, Zhitong Xiong, Ioannis Papoutsis, Gustau Camps-Valls, Xiao Xiang Zhu
In that direction, we propose integrating causality with Graph Neural Networks (GNNs) that explicitly model the causal mechanism among complex variables via graph learning.
1 code implementation • 3 Mar 2024 • Chenying Liu, Conrad M Albrecht, Yi Wang, Qingyu Li, Xiao Xiang Zhu
AIO2 utilizes a mean teacher model to enhance training robustness with noisy labels to both stabilize the training accuracy curve for fitting in ACT and provide pseudo labels for correction in O2C.
no code implementations • 25 Feb 2024 • Chenying Liu, Conrad Albrecht, Yi Wang, Xiao Xiang Zhu
In this work, we propose to explore the under-exploited potential of noisy labels for segmentation task specific pretraining, and exam its robustness when confronted with mismatched categories and different decoders during fine-tuning.
no code implementations • 21 Feb 2024 • Adrian Höhl, Ivica Obadic, Miguel Ángel Fernández Torres, Hiba Najjar, Dario Oliveira, Zeynep Akata, Andreas Dengel, Xiao Xiang Zhu
In recent years, black-box machine learning approaches have become a dominant modeling paradigm for knowledge extraction in Remote Sensing.
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 • 31 Jan 2024 • Shan Zhao, Zhitong Xiong, Xiao Xiang Zhu
Subseasonal forecasting, which is pivotal for agriculture, water resource management, and early warning of disasters, faces challenges due to the chaotic nature of the atmosphere.
1 code implementation • 17 Jan 2024 • Konrad Heidler, Ingmar Nitze, Guido Grosse, Xiao Xiang Zhu
To improve model generalization across the Arctic without the need for additional labelled data, we present a semi-supervised learning approach to train semantic segmentation models to detect RTS.
no code implementations • 15 Jan 2024 • Zhitong Xiong, Yi Wang, Fahong Zhang, Xiao Xiang Zhu
Current remote sensing foundation models typically specialize in a single modality or a specific spatial resolution range, limiting their versatility for downstream datasets.
no code implementations • 15 Nov 2023 • Katharina Hechinger, Christoph Koller, Xiao Xiang Zhu, Göran Kauermann
In supervised learning, uncertainty can already occur in the very first stage of the training process, the labelling step.
1 code implementation • 28 Oct 2023 • Yi Wang, Hugo Hernández Hernández, Conrad M Albrecht, Xiao Xiang Zhu
Self-supervised learning guided by masked image modelling, such as Masked AutoEncoder (MAE), has attracted wide attention for pretraining vision transformers in remote sensing.
Ranked #1 on Multi-Label Image Classification on BigEarthNet-S1 (official test set) (using extra training data)
no code implementations • 8 Oct 2023 • Qingsong Xu, Yilei Shi, Jonathan Bamber, Ye Tuo, Ralf Ludwig, Xiao Xiang Zhu
Specifically, we present a comprehensive review of the physics-aware ML methods, building a structured community (PaML) of existing methodologies that integrate prior physical knowledge or physics-based modeling into ML.
no code implementations • 28 Sep 2023 • Kun Qian, Yuanyuan Wang, Peter Jung, Yilei Shi, Xiao Xiang Zhu
Deep neural networks based on unrolled iterative algorithms have achieved remarkable success in sparse reconstruction applications, such as synthetic aperture radar (SAR) tomographic inversion (TomoSAR).
1 code implementation • 28 Sep 2023 • Sining Chen, Yilei Shi, Zhitong Xiong, Xiao Xiang Zhu
To tackle this problem, we propose a method for monocular height estimation from optical imagery, which is currently one of the richest sources of remote sensing data.
no code implementations • 26 Sep 2023 • Danfeng Hong, Bing Zhang, Hao Li, YuXuan Li, Jing Yao, Chenyu Li, Martin Werner, Jocelyn Chanussot, Alexander Zipf, Xiao Xiang Zhu
Artificial intelligence (AI) approaches nowadays have gained remarkable success in single-modality-dominated remote sensing (RS) applications, especially with an emphasis on individual urban environments (e. g., single cities or regions).
no code implementations • 20 Sep 2023 • Fahong Zhang, Yilei Shi, Xiao Xiang Zhu
A promising method to address this problem is domain adaptation, where the training and the testing datasets are split into two or multiple domains according to their distributions, and an adaptation method is applied to improve the generalizability of the model on the testing dataset.
1 code implementation • 19 Sep 2023 • Fahong Zhang, Yilei Shi, Zhitong Xiong, Xiao Xiang Zhu
In this context, few-shot object detection (FSOD) has emerged as a promising direction, which aims at enabling the model to detect novel objects with only few of them annotated.
1 code implementation • 14 Sep 2023 • Yao Sun, Anna Kruspe, Liqiu Meng, Yifan Tian, Eike J Hoffmann, Stefan Auer, Xiao Xiang Zhu
This work addresses the challenges in applying Scene Text Recognition (STR) in crowdsourced street-view images for building attribute mapping.
no code implementations • 11 Sep 2023 • Shan Zhao, Sudipan Saha, Zhitong Xiong, Niklas Boers, Xiao Xiang Zhu
Motivated by this, we explore a geometric deep learning-based temporal Graph Convolutional Network (GCN) for precipitation nowcasting.
2 code implementations • 11 Sep 2023 • Yi Wang, Conrad M Albrecht, Nassim Ait Ali Braham, Chenying Liu, Zhitong Xiong, Xiao Xiang Zhu
We propose Decoupling Common and Unique Representations (DeCUR), a simple yet effective method for multimodal self-supervised learning.
1 code implementation • 4 Aug 2023 • Yi Wang, Chenying Liu, Arti Tiwari, Micha Silver, Arnon Karnieli, Xiao Xiang Zhu, Conrad M Albrecht
Discovering ancient agricultural terraces in desert regions is important for the monitoring of long-term climate changes on the Earth's surface.
1 code implementation • 2 Aug 2023 • Qingsong Xu, Yilei Shi, Jianhua Guo, Chaojun Ouyang, Xiao Xiang Zhu
Specifically, a transformer-driven image translation composed of a light-weight transformer and a domain-specific affinity weight is first proposed to mitigate domain shift between two images with real-time efficiency.
1 code implementation • 17 Jul 2023 • Zhaiyu Chen, Yilei Shi, Liangliang Nan, Zhitong Xiong, Xiao Xiang Zhu
We present PolyGNN, a polyhedron-based graph neural network for 3D building reconstruction from point clouds.
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 • 19 Jun 2023 • Shivam Pande, Nassim Ait Ali Braham, Yi Wang, Conrad M Albrecht, Biplab Banerjee, Xiao Xiang Zhu
Recently, to effectively train the deep learning models with minimal labelled samples, the unlabeled samples are also being leveraged in self-supervised and semi-supervised setting.
1 code implementation • 16 Jun 2023 • Qingsong Xu, Yilei Shi, Xiao Xiang Zhu
It consists of two stages, space granulation and attribute granulation.
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.
1 code implementation • NeurIPS 2023 • Alexandre Lacoste, Nils Lehmann, Pau Rodriguez, Evan David Sherwin, Hannah Kerner, Björn Lütjens, Jeremy Andrew Irvin, David Dao, Hamed Alemohammad, Alexandre Drouin, Mehmet Gunturkun, Gabriel Huang, David Vazquez, Dava Newman, Yoshua Bengio, Stefano Ermon, Xiao Xiang Zhu
Recent progress in self-supervision has shown that pre-training large neural networks on vast amounts of unsupervised data can lead to substantial increases in generalization to downstream tasks.
no code implementations • 4 Jun 2023 • Zhitong Xiong, Yanfeng Liu, Qi Wang, Xiao Xiang Zhu
We present the RSSOD-Bench dataset for salient object detection (SOD) in optical remote sensing imagery.
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 • 23 May 2023 • Kun Qian, Yuanyuan Wang, Peter Jung, Yilei Shi, Xiao Xiang Zhu
An emerging technique known as deep unrolling provided a good combination of the descriptive ability of neural networks, explainable, and computational efficiency for BPDN.
no code implementations • 15 May 2023 • Devis Tuia, Konrad Schindler, Begüm Demir, Gustau Camps-Valls, Xiao Xiang Zhu, Mrinalini Kochupillai, Sašo Džeroski, Jan N. van Rijn, Holger H. Hoos, Fabio Del Frate, Mihai Datcu, Jorge-Arnulfo Quiané-Ruiz, Volker Markl, Bertrand Le Saux, Rochelle Schneider
Earth observation (EO) is a prime instrument for monitoring land and ocean processes, studying the dynamics at work, and taking the pulse of our planet.
2 code implementations • 9 May 2023 • Xiang Li, Congcong Wen, Yuan Hu, Zhenghang Yuan, Xiao Xiang Zhu
Existing AI-related research in remote sensing primarily focuses on visual understanding tasks while neglecting the semantic understanding of the objects and their relationships.
no code implementations • 8 May 2023 • Yilei Shi, Richard Bamler, Yuanyuan Wang, Xiao Xiang Zhu
Multi-baseline interferometric synthetic aperture radar (InSAR) techniques are effective approaches for retrieving the 3-D information of urban areas.
1 code implementation • 5 May 2023 • Iris de Gélis, Sudipan Saha, Muhammad Shahzad, Thomas Corpetti, Sébastien Lefèvre, Xiao Xiang Zhu
To circumnavigate this dependence, we propose an unsupervised 3D point cloud change detection method mainly based on self-supervised learning using deep clustering and contrastive learning.
no code implementations • 4 May 2023 • Daniel Racek, Brittany I. Davidson, Paul W. Thurner, Xiao Xiang Zhu, Göran Kauermann
Notably, we find that more than half of the Russian-tweeting users shift towards Ukrainian as a result of the war.
1 code implementation • 11 Apr 2023 • Patrick Ebel, Vivien Sainte Fare Garnot, Michael Schmitt, Jan Dirk Wegner, Xiao Xiang Zhu
Clouds and haze often occlude optical satellite images, hindering continuous, dense monitoring of the Earth's surface.
Ranked #1 on Cloud Removal on SEN12MS-CR
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.
1 code implementation • 26 Jan 2023 • Qingsong Xu, Yilei Shi, Xin Yuan, Xiao Xiang Zhu
Empirical results show that the proposed model is effective and practical for remote sensing image scene classification, regardless of whether the source data is available or not.
1 code implementation • 9 Jan 2023 • Fang Xu, Yilei Shi, Patrick Ebel, Wen Yang, Xiao Xiang Zhu
In this paper, we introduce Planet-CR, a benchmark dataset for high-resolution cloud removal with multi-modal and multi-resolution data fusion.
3 code implementations • 13 Nov 2022 • Yi Wang, Nassim Ait Ali Braham, Zhitong Xiong, Chenying Liu, Conrad M Albrecht, Xiao Xiang Zhu
Self-supervised pre-training bears potential to generate expressive representations without human annotation.
Ranked #1 on Multi-Label Image Classification on BigEarthNet (official test set) (using extra training data)
no code implementations • 1 Nov 2022 • Xiao Xiang Zhu, Yuanyuan Wang, Mrinalini Kochupillai, Martin Werner, Matthias Häberle, Eike Jens Hoffmann, Hannes Taubenböck, Devis Tuia, Alex Levering, Nathan Jacobs, Anna Kruspe, Karam Abdulahhad
In this article, we address key aspects in the field, including data availability, analysis-ready data preparation and data management, geo-information extraction from social media text messages and images, and the fusion of social media and remote sensing data.
no code implementations • 24 Oct 2022 • Ivica Obadic, Ribana Roscher, Dario Augusto Borges Oliveira, Xiao Xiang Zhu
Using explainable machine learning to reveal the inner workings of these models is an important step towards improving stakeholders' trust and efficient agriculture monitoring.
1 code implementation • Experiments in Fluids 2022 • Rıdvan Salih Kuzu, Philipp Mühlmann, Xiao Xiang Zhu
Many of the laminar-turbulent flow localisation techniques are strongly dependent upon expert control even-though determining the flow distribution is the prerequisite for analysing the efficiency of wing & stabiliser design in aeronautics.
Laminar-Turbulent Flow Localisation Self-Supervised Learning
no code implementations • 10 Oct 2022 • Zhitong Xiong, Fahong Zhang, Yi Wang, Yilei Shi, Xiao Xiang Zhu
Furthermore, a new platform for EO, termed EarthNets, is released to achieve a fair and consistent evaluation of deep learning methods on remote sensing 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.
no code implementations • 6 Sep 2022 • Omid Ghorbanzadeh, Yonghao Xu, Hengwei Zhao, Junjue Wang, Yanfei Zhong, Dong Zhao, Qi Zang, Shuang Wang, Fahong Zhang, Yilei Shi, Xiao Xiang Zhu, Lin Bai, Weile Li, Weihang Peng, Pedram Ghamisi
The objective of the competition is to automatically detect landslides based on large-scale multiple sources of satellite imagery collected globally.
1 code implementation • 1 Sep 2022 • Xin-Yi Tong, Gui-Song Xia, Xiao Xiang Zhu
To validate the generalizability of our dataset and the proposed approach across different sensors and different geographical regions, we carry out land cover mapping on five megacities in China and six cities in other five Asian countries severally using: PlanetScope (3 m), Gaofen-1 (8 m), and Sentinel-2 (10 m) satellite images.
no code implementations • 4 Aug 2022 • Kalifou René Traoré, Andrés Camero, Xiao Xiang Zhu
Hyperparameter optimization (HPO) is a well-studied research field.
1 code implementation • 30 Jul 2022 • Zhitong Xiong, Haopeng Li, Xiao Xiang Zhu
To address this problem, we propose to aggregate the learnable covariance matrices with a deformable 4D Transformer to effectively predict the segmentation map.
Ranked #1 on Few-Shot Semantic Segmentation on FSS-1000 (5-shot)
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.
1 code implementation • CVPR2022W 2022 • Codruţ-Andrei Diaconu, Sudipan Saha, Stephan Günnemann, Xiao Xiang Zhu
Climate change is perhaps the biggest single threat to humankind and the environment, as it severely impacts our terrestrial surface, home to most of the living species.
Ranked #2 on Earth Surface Forecasting on EarthNet2021 OOD Track
no code implementations • 14 Jun 2022 • Conrad M Albrecht, Chenying Liu, Yi Wang, Levente Klein, Xiao Xiang Zhu
We present and evaluate a weakly-supervised methodology to quantify the spatio-temporal distribution of urban forests based on remotely sensed data with close-to-zero human interaction.
1 code implementation • 6 Jun 2022 • Fang Xu, Yilei Shi, Patrick Ebel, Lei Yu, Gui-Song Xia, Wen Yang, Xiao Xiang Zhu
The challenge of the cloud removal task can be alleviated with the aid of Synthetic Aperture Radar (SAR) images that can penetrate cloud cover.
Ranked #2 on Cloud Removal on SEN12MS-CR
1 code implementation • 30 May 2022 • Christoph Koller, Göran Kauermann, Xiao Xiang Zhu
Technological and computational advances continuously drive forward the broad field of deep learning.
no code implementations • 17 May 2022 • Qingyu Li, Yilei Shi, Xiao Xiang Zhu
Considering that rich information is also encoded in feature maps, we propose to integrate the consistency of both features and outputs in the end-to-end network training of unlabeled samples, enabling to impose additional constraints.
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.
2 code implementations • 11 Apr 2022 • Yi Wang, Conrad M Albrecht, Xiao Xiang Zhu
Experimental results employing the BigEarthNet-MM dataset demonstrate the benefits of both, the ViT backbones and the proposed multimodal SSL algorithm DINO-MM.
1 code implementation • 7 Apr 2022 • Sugandha Doda, Yuanyuan Wang, Matthias Kahl, Eike Jens Hoffmann, Kim Ouan, Hannes Taubenböck, Xiao Xiang Zhu
Obtaining a dynamic population distribution is key to many decision-making processes such as urban planning, disaster management and most importantly helping the government to better allocate socio-technical supply.
no code implementations • CVPR 2022 • Aysim Toker, Lukas Kondmann, Mark Weber, Marvin Eisenberger, Andrés Camero, Jingliang Hu, Ariadna Pregel Hoderlein, Çağlar Şenaras, Timothy Davis, Daniel Cremers, Giovanni Marchisio, Xiao Xiang Zhu, Laura Leal-Taixé
These observations are paired with pixel-wise monthly semantic segmentation labels of 7 land use and land cover (LULC) classes.
no code implementations • 15 Feb 2022 • Eike Jens Hoffmann, Karam Abdulahhad, Xiao Xiang Zhu
To cope with this issue this study proposes a filtering pipeline to yield high quality, ground level imagery from large social media image datasets.
no code implementations • 17 Jan 2022 • Kalifou René Traoré, Andrés Camero, Xiao Xiang Zhu
With the rapid rise of neural architecture search, the ability to understand its complexity from the perspective of a search algorithm is desirable.
1 code implementation • 17 Jan 2022 • Zhitong Xiong, Sining Chen, Yilei Shi, Xiao Xiang Zhu
Furthermore, a novel unsupervised semantic segmentation task based on height estimation is first introduced in this work.
no code implementations • 30 Dec 2021 • Zhitong Xiong, Wei Huang, Jingtao Hu, Xiao Xiang Zhu
Therefore, we propose a new benchmark dataset to study the transferability of height estimation models in a cross-dataset setting.
no code implementations • 8 Dec 2021 • Kun Qian, Yuanyuan Wang, Yilei Shi, Xiao Xiang Zhu
This superior performance comes at the cost of extra computational burdens, because of the sparse reconstruction, which cannot be solved analytically and we need to employ computationally expensive iterative solvers.
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 • 5 Nov 2021 • Kalifou René Traoré, Andrés Camero, Xiao Xiang Zhu
First, we perform a calibrated clustering analysis of the search space, and second, we extract the centroids and use them to initialize a NAS algorithm.
no code implementations • 2 Nov 2021 • Kalifou René Traoré, Andrés Camero, Xiao Xiang Zhu
In this paper, we propose to use fitness landscape analysis to study a neural architecture search problem.
1 code implementation • 11 Oct 2021 • Fei Zhou, Xin Sun, Junyu Dong, Haoran Zhao, Xiao Xiang Zhu
Although Convolution Neural Networks (CNNs) has made substantial progress in the low-light image enhancement task, one critical problem of CNNs is the paradox of model complexity and performance.
no code implementations • 5 Oct 2021 • Lukas Kondmann, Aysim Toker, Sudipan Saha, Bernhard Schölkopf, Laura Leal-Taixé, Xiao Xiang Zhu
It uses this model to analyze differences in the pixel and its spatial context-based predictions in subsequent time periods for change detection.
no code implementations • 26 Aug 2021 • Sudipan Saha, Shan Zhao, Nasrullah Sheikh, Xiao Xiang Zhu
Multi-target domain adaptation is a powerful extension in which a single classifier is learned for multiple unlabeled target domains.
no code implementations • 20 Aug 2021 • Kalifou Rene Traore, Andrés Camero, Xiao Xiang Zhu
In this study, we propose to accelerate a NAS algorithm using a data-driven initialization technique, leveraging the availability of NAS benchmarks.
no code implementations • 4 Aug 2021 • Lukas Kondmann, Xiao Xiang Zhu
Our findings indicate that poverty is systematically overestimated and electricity systematically underestimated for scheduled tribes in comparison to a synthetic counterfactual group of villages.
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.
no code implementations • 7 Jul 2021 • Jakob Gawlikowski, Cedrique Rovile Njieutcheu Tassi, Mohsin Ali, JongSeok Lee, Matthias Humt, Jianxiang Feng, Anna Kruspe, Rudolph Triebel, Peter Jung, Ribana Roscher, Muhammad Shahzad, Wen Yang, Richard Bamler, Xiao Xiang Zhu
Different examples from the wide spectrum of challenges in different fields give an idea of the needs and challenges regarding uncertainties in practical applications.
1 code implementation • 21 May 2021 • Danfeng Hong, Jingliang Hu, Jing Yao, Jocelyn Chanussot, Xiao Xiang Zhu
Moreover, to better assess multimodal baselines and the newly-proposed S2FL model, three multimodal RS benchmark datasets, i. e., Houston2013 -- hyperspectral and multispectral data, Berlin -- hyperspectral and synthetic aperture radar (SAR) data, Augsburg -- hyperspectral, SAR, and digital surface model (DSM) data, are released and used for land cover classification.
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.
no code implementations • 26 Apr 2021 • Konstantin Klemmer, Sudipan Saha, Matthias Kahl, Tianlin Xu, Xiao Xiang Zhu
Deep generative models are increasingly used to gain insights in the geospatial data domain, e. g., for climate data.
1 code implementation • 22 Apr 2021 • Yuansheng Hua, Lichao Moua, Jianzhe Lin, Konrad Heidler, Xiao Xiang Zhu
To be more specific, we first learn the prototype representation of each aerial scene from single-scene aerial image datasets and store it in an external memory.
1 code implementation • 11 Apr 2021 • Devis Tuia, Ribana Roscher, Jan Dirk Wegner, Nathan Jacobs, Xiao Xiang Zhu, Gustau Camps-Valls
In the last years we have witnessed the fields of geosciences and remote sensing and artificial intelligence to become closer.
no code implementations • 9 Apr 2021 • Sudipan Saha, Biplab Banerjee, Xiao Xiang Zhu
Deep learning (DL) based supervised change detection (CD) models require large labeled training data.
no code implementations • 9 Apr 2021 • Jakob Gawlikowski, Sudipan Saha, Anna Kruspe, Xiao Xiang Zhu
In satellite image analysis, distributional mismatch between the training and test data may arise due to several reasons, including unseen classes in the test data and differences in the geographic area.
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.
no code implementations • 2 Mar 2021 • Danfeng Hong, wei he, Naoto Yokoya, Jing Yao, Lianru Gao, Liangpei Zhang, Jocelyn Chanussot, Xiao Xiang Zhu
Hyperspectral imaging, also known as image spectrometry, is a landmark technique in geoscience and remote sensing (RS).
1 code implementation • 22 Feb 2021 • Lei Ding, Hao Tang, Yahui Liu, Yilei Shi, Xiao Xiang Zhu, Lorenzo Bruzzone
To address this issue, we propose an adversarial shape learning network (ASLNet) to model the building shape patterns that improve the accuracy of building segmentation.
no code implementations • 12 Feb 2021 • Sudipan Saha, Patrick Ebel, Xiao Xiang Zhu
In particular, we are interested in the combination of the images acquired by optical and Synthetic Aperture Radar (SAR) sensors.
no code implementations • 9 Feb 2021 • Jay Nandy, Sudipan Saha, Wynne Hsu, Mong Li Lee, Xiao Xiang Zhu
In this paper, we propose a novel method, called \emph{Certification through Adaptation}, that transforms an AT model into a randomized smoothing classifier during inference to provide certified robustness for $\ell_2$ norm without affecting their empirical robustness against adversarial attacks.
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 • 29 Nov 2020 • Saqib Ali Khan, Yilei Shi, Muhammad Shahzad, Xiao Xiang Zhu
In this letter, we have proposed an alternative approach to overcome the limitations of CNN based approaches by encoding the spatial features of raw 3D point clouds into undirected symmetrical graph models.
no code implementations • 23 Nov 2020 • Chunping Qiu, Lukas Liebel, Lloyd H. Hughes, Michael Schmitt, Marco Körner, Xiao Xiang Zhu
Human Settlement Extent (HSE) and Local Climate Zone (LCZ) maps are both essential sources, e. g., for sustainable urban development and Urban Heat Island (UHI) studies.
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 • 5 Oct 2020 • Ruchika Chavhan, Biplab Banerjee, Xiao Xiang Zhu, Subhasis Chaudhuri
We deal with the problem of generating textual captions from optical remote sensing (RS) images using the notion of deep reinforcement learning.
1 code implementation • 21 Sep 2020 • Danfeng Hong, Naoto Yokoya, Jocelyn Chanussot, Jian Xu, Xiao Xiang Zhu
Conventional nonlinear subspace learning techniques (e. g., manifold learning) usually introduce some drawbacks in explainability (explicit mapping) and cost-effectiveness (linearization), generalization capability (out-of-sample), and representability (spatial-spectral discrimination).
no code implementations • 2 Sep 2020 • Yuanyuan Wang, Xiao Xiang Zhu
Layover separation has been fundamental to many synthetic aperture radar applications, such as building reconstruction and biomass estimation.
no code implementations • 27 Aug 2020 • Anna Kruspe, Matthias Häberle, Iona Kuhn, Xiao Xiang Zhu
We separate the results by country of origin, and correlate their temporal development with events in those countries.
no code implementations • 3 Aug 2020 • Philipp Sibler, Yuanyuan Wang, Stefan Auer, Mohsin Ali, Xiao Xiang Zhu
Generative Adversarial Networks (GANs) have been employed with certain success for image translation tasks between optical and real-valued SAR intensity imagery.
no code implementations • 17 Jul 2020 • Danfeng Hong, Jing Yao, Xin Wu, Jocelyn Chanussot, Xiao Xiang Zhu
In recent years, hyperspectral imaging, also known as imaging spectroscopy, has been paid an increasing interest in geoscience and remote sensing community.
1 code implementation • 2 Jul 2020 • Andrea Meraner, Patrick Ebel, Xiao Xiang Zhu, Michael Schmitt
Optical remote sensing imagery is at the core of many Earth observation activities.
Ranked #3 on Cloud Removal on SEN12MS-CR
no code implementations • ACL 2020 • Anna Kruspe, Matthias H{\"a}berle, Iona Kuhn, Xiao Xiang Zhu
In this paper, we analyze Twitter messages (tweets) collected during the first months of the COVID-19 pandemic in Europe with regard to their sentiment.
no code implementations • 29 Jun 2020 • Nan Ge, Richard Bamler, Danfeng Hong, Xiao Xiang Zhu
This paper addresses the general problem of single-look multi-master SAR tomography.
no code implementations • 24 Jun 2020 • Danfeng Hong, Naoto Yokoya, Gui-Song Xia, Jocelyn Chanussot, Xiao Xiang Zhu
This paper addresses the problem of semi-supervised transfer learning with limited cross-modality data in remote sensing.
1 code implementation • 22 Jun 2020 • Yang Long, Gui-Song Xia, Shengyang Li, Wen Yang, Michael Ying Yang, Xiao Xiang Zhu, Liangpei Zhang, Deren Li
After reviewing existing benchmark datasets in the research community of RS image interpretation, this article discusses the problem of how to efficiently prepare a suitable benchmark dataset for RS image interpretation.
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 • 16 May 2020 • Chunping Qiu, Xiaochong Tong, Michael Schmitt, Benjamin Bechtel, Xiao Xiang Zhu
As a unique classification scheme for urban forms and functions, the local climate zone (LCZ) system provides essential general information for any studies related to urban environments, especially on a large scale.
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 • 17 Mar 2020 • Yilei Shi, Richard Bamler, Yuanyuan Wang, Xiao Xiang Zhu
Multi-baseline interferometric synthetic aperture radar (InSAR) techniques are effective approaches for retrieving the 3-D information of urban areas.
1 code implementation • 19 Feb 2020 • Michael Schmitt, Jonathan Prexl, Patrick Ebel, Lukas Liebel, Xiao Xiang Zhu
Therefore, this paper seeks to make a case for the application of weakly supervised learning strategies to get the most out of available data sources and achieve progress in high-resolution large-scale land cover mapping.
Weakly-supervised Learning Weakly supervised Semantic Segmentation +1
no code implementations • 11 Feb 2020 • Qingyu Li, Yilei Shi, Xin Huang, Xiao Xiang Zhu
Due to the complexity of buildings, the accurate and reliable generation of the building footprint from remote sensing imagery is still a challenging task.
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
no code implementations • 18 Dec 2019 • Danfeng Hong, Xin Wu, Pedram Ghamisi, Jocelyn Chanussot, Naoto Yokoya, Xiao Xiang Zhu
In this paper, we propose a solution to address this issue by locally extracting invariant features from hyperspectral imagery (HSI) in both spatial and frequency domains, using a method called invariant attribute profiles (IAPs).
no code implementations • 18 Dec 2019 • Danfeng Hong, Jocelyn Chanussot, Naoto Yokoya, Jian Kang, Xiao Xiang Zhu
Due to the ever-growing diversity of the data source, multi-modality feature learning has attracted more and more attention.
no code implementations • 8 Nov 2019 • Yilei Shi, Qingyu Li, Xiao Xiang Zhu
Taking the semantic segmentation of building footprints as a practical example, we compared different feature embedding architectures and graph neural networks.
no code implementations • 23 Aug 2019 • Yuxing Xie, Jiaojiao Tian, Xiao Xiang Zhu
3D Point Cloud Semantic Segmentation (PCSS) is attracting increasing interest, due to its applicability in remote sensing, computer vision and robotics, and due to the new possibilities offered by deep learning techniques.
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.
2 code implementations • 18 Jun 2019 • Michael Schmitt, Lloyd Haydn Hughes, Chunping Qiu, Xiao Xiang Zhu
The availability of curated large-scale training data is a crucial factor for the development of well-generalizing deep learning methods for the extraction of geoinformation from multi-sensor remote sensing imagery.
no code implementations • 13 Jun 2019 • Jingliang Hu, Danfeng Hong, Xiao Xiang Zhu
Multi-modal data fusion has recently been shown promise in classification tasks in remote sensing.
no code implementations • 29 May 2019 • Guichen Zhang, Pedram Ghamisi, Xiao Xiang Zhu
This paper proposes a novel framework for fusing multi-temporal, multispectral satellite images and OpenStreetMap (OSM) data for the classification of local climate zones (LCZs).
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 • 9 Jan 2019 • Danfeng Hong, Naoto Yokoya, Nan Ge, Jocelyn Chanussot, Xiao Xiang Zhu
In this paper, we aim at tackling a general but interesting cross-modality feature learning question in remote sensing community --- can a limited amount of highly-discrimin-ative (e. g., hyperspectral) training data improve the performance of a classification task using a large amount of poorly-discriminative (e. g., multispectral) data?
no code implementations • 30 Dec 2018 • Danfeng Hong, Naoto Yokoya, Jocelyn Chanussot, Xiao Xiang Zhu
To achieve accurate land cover classification over a large coverage, we propose a cross-modality feature learning framework, called common subspace learning (CoSpace), by jointly considering subspace learning and supervised classification.
no code implementations • 5 Nov 2018 • Yilei Shi, Xiao Xiang Zhu, Richard Bamler
We propose to increase SNR by integrating non-local estimation into the inversion and show that a reasonable reconstruction of buildings from only seven interferograms is feasible.
no code implementations • 29 Oct 2018 • Danfeng Hong, Naoto Yokoya, Jocelyn Chanussot, Xiao Xiang Zhu
To this end, we propose a novel spectral mixture model, called the augmented linear mixing model (ALMM), to address spectral variability by applying a data-driven learning strategy in inverse problems of hyperspectral unmixing.
no code implementations • 26 Oct 2018 • Yilei Shi, Qingyu Li, Xiao Xiang Zhu
The automatic generation of building footprints from satellite images presents a considerable challenge due to the complexity of building shapes.
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 • 14 Aug 2018 • Muhammad Shahzad, Michael Maurer, Friedrich Fraundorfer, Yuanyuan Wang, Xiao Xiang Zhu
This paper addresses the highly challenging problem of automatically detecting man-made structures especially buildings in very high resolution (VHR) synthetic aperture radar (SAR) images.
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 • 4 Jul 2018 • Michael Schmitt, Lloyd Haydn Hughes, Xiao Xiang Zhu
While deep learning techniques have an increasing impact on many technical fields, gathering sufficient amounts of training data is a challenging problem in remote sensing.
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 Feb 2018 • Jian Kang, Marco Körner, Yuanyuan Wang, Hannes Taubenböck, Xiao Xiang Zhu
The proposed method is based on Convolutional Neural Networks (CNNs) which classify facade structures from street view images, such as Google StreetView, in addition to remote sensing images which usually only show roof structures.
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.