LKLukas Kondmann

Lukas Kondmann

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lukas Kondmann has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Geography-Aware Masked Autoencoders for Change Detection in Remote Sensing

    by Lukas Kondmann, Caglar Senaras, Yuki M. Asano, Akhil Singh Rana, Annett Wania, Xiao Xiang Zhu

    Increasing coverage of commercial and public satellites allows us to monitor the pulse of the Earth in ever-shorter frequency (Zhu et al., 2017). Together with the rise of deep learning in artificial intelligence (AI) (LeCun et al., 2015), the field of AI for Earth Observation (AI4EO) is growing rapidly. However, many supervised deep learning techniques are data-hungry, which means that annotated data in large quantities are necessary to help these algorithms reach their full potential. In many Earth Observation applications such as change detection, this is often infeasible because high-quality annotations require manual labeling which is time-consuming and costly. Self-supervised learning (SSL) can help tackle the issue of limited label availability in AI4EO. In SSL, an algorithm is pretrained with tasks that only require the input data without annotation. Notably, Masked Autoencoders (MAE) have shown promising performances recently where a Vision Transformer learns to reconstruct a full image with only 25% of it as input. We hypothesize that the success of MAEs also extends to satellite imagery and evaluate this with a change detection downstream task. In addition, we provide a multitemporal DINO baseline which is another widely successful SSL method. Further, we test a second version of MAEs, which we call GeoMAE. GeoMAE incorporates the location and date of the satellite image as auxiliary information in self-supervised pretraining. The coordinates and date information are passed as additional tokens to the MAE model similar to the positional encoding. The pretraining dataset used is the RapidAI4EO corpus which contains multi-temporal Planet Fusion imagery for a variety of locations across Europe. The dataset for the downstream task also uses Planet Fusion in pairs as input data. These are provided on a 600m * 600m patch level three months apart together with a classification if the respective patch has changed in this period. Self-supervised pretraining is done for up to 150 epochs where we take the model with the best validation performance on the downstream task as a starting point for the test set. We find that the regular MAE model scores the best on the test set with an accuracy of 81.54% followed by DINO with 80.63% and GeoMAE with 80.02%. Pretraining MAE with ImageNet data instead of satellite images results in a notable performance loss down to 71.36%. Overall, our current pretraining experiments can not yet confirm our hypothesis that GeoMAE is advantageous compared to regular MAE. However, in similar spirit, Cong et al. (2022) recently introduced SatMAE which outlines that for other remote sensing applications, the combination of auxiliary information and novel masking strategies is a key factor. Therefore, it seems that a combination of location and time inputs together with adapted masking may also hold the most potential for change detection. There is ample potential for future research in geo-specific applications of MAEs and we provide a starting point for this with our experimental results for change detection.


  • Open Access

    SemiSiROC: Semisupervised Change Detection With Optical Imagery and an Unsupervised Teacher Model

    by Lukas Kondmann, Sudipan Saha, Xiao Xiang Zhu

    Change detection is an important yet challenging task in remote sensing. In this paper, we underline that the combination of unsupervised and supervised methods in a semi-supervised framework improves change detection performance. We rely on Half-Sibling Regression for Optical Change Detection (SiROC) as an unsupervised teacher model to generate pseudo labels and select only the most confident pseudo labels for pretraining different student models. Our results are robust to three different competitive student models, two semi-supervised pseudo label baselines, two benchmark datasets and a variety of loss functions. While the performance gains are highest with a limited number of labels, a notable effect of pseudo label pretraining persists when more labeled data is used. Further, we outline that the confidence selection of SiROC is indeed effective and that the performance gains generalize to scenes that were not used for pseudo label training. Through the pseudo label pretraining, SemiSiROC allows student models to learn more refined shapes of changes and makes them less sensitive to differences in acquisition conditions.


  • Open Access

    Spatial Context Awareness for Unsupervised Change Detection in Optical Satellite Images

    by Lukas Kondmann, Aysim Toker, Sudipan Saha, Bernhard Scholkopf, Laura Leal-Taixe, Xiao Xiang Zhu

    Detecting changes on the ground in multitemporal Earth observation data is one of the key problems in remote sensing. In this article, we introduce Sibling Regression for Optical Change detection (SiROC), an unsupervised method for change detection (CD) in optical satellite images with medium and high resolutions. SiROC is a spatial context-based method that models a pixel as a linear combination of its distant neighbors. It uses this model to analyze differences in the pixel and its spatial context-based predictions in subsequent time periods for CD. We combine this spatial context-based CD with ensembling over mutually exclusive neighborhoods and transitioning from pixel to object-level changes with morphological operations. SiROC achieves competitive performance for CD with medium-resolution Sentinel-2 and high-resolution Planetscope imagery on four datasets. Besides accurate predictions without the need for training, SiROC also provides a well-calibrated uncertainty of its predictions.


  • Open Access

    Change Detection in Hyperdimensional Images Using Untrained Models

    by Sudipan Saha, Lukas Kondmann, Qian Song, Xiao Xiang Zhu

    Deep transfer-learning-based change detection methods are dependent on the availability of sensor-specific pretrained feature extractors. Such feature extractors are not always available due to lack of training data, especially for hyperspectral sensors and other hyperdimensional images. Moreover models trained on easily available multispectral (RGB/RGB-NIR) images cannot be reused on such hyperdimensional images due to their irregular number of bands. While hyperdimensional images show large number of spectral bands, they generally show much less spatial complexity, thus reducing the requirement of large receptive fields of convolution filters. Recent works in the computer vision have shown that even untrained deep models can yield remarkable result in some tasks like super-resolution and surface reconstruction. This motivates us to make a bold proposition that untrained lightweight deep model, initialized with some weight initialization strategy, can be used to extract useful semantic features from bi-temporal hyperdimensional images. Based on this proposition, we design a novel change detection framework for hyperdimensional images by extracting bitemporal features using an untrained model and further comparing the extracted features using deep change vector analysis to distinguish changed pixels from the unchanged ones. We further use the deep change hypervectors to cluster the changed pixels into different semantic groups. We conduct experiments on four change detection datasets: three hyperspectral datasets and a hyperdimensional polarimetric synthetic aperture radar dataset. The results clearly demonstrate that the proposed method is suitable for change detection in hyperdimensional remote sensing data.