检索结果-内蒙古大学图书馆

Deep learning-based bathymetry retrieval without in-situ depths using remote sensing imagery and SfM-MVS DSMs with data gaps

学校读者我要写书评

暂无评论

ISPRS Journal of Photogrammetry and Remote Sensing 2025年 225卷 341-361页

作者： Agrafiotis, Panagiotis Demir, Begüm Faculty of Electrical Engineering and Computer Science Technische Universität Berlin Berlin10587 Germany BIFOLD - Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany

Accurate, detailed, and high-frequent bathymetry is crucial for shallow seabed areas facing intense climatological and anthropogenic pressures. Current methods utilizing airborne or satellite optical imagery to derive bathymetry primarily rely on either Structure-from-Motion and Multi-View Stereo (SfM-MVS) with refraction correction or Spectrally Derived Bathymetry (SDB). However, SDB methods often require extensive manual fieldwork or costly reference data, while SfM-MVS approaches face challenges even after refraction correction. These include depth data gaps and noise in environments with homogeneous visual textures, which hinder the creation of accurate and complete Digital Surface Models (DSMs) of the seabed. To address these challenges, this work introduces a methodology that combines the high-fidelity 3D reconstruction capabilities of the SfM-MVS methods with state-of-the-art refraction correction techniques, along with the spectral analysis capabilities of a new deep learning-based method for bathymetry prediction. This integration enables a synergistic approach where SfM-MVS derived DSMs with data gaps are used as training data to generate complete bathymetric maps. In this context, we propose Swin-BathyUNet that combines U-Net with Swin Transformer self-attention layers and a cross-attention mechanism, specifically tailored for SDB. Swin-BathyUNet is designed to improve bathymetric accuracy by capturing long-range spatial relationships and can also function as a standalone solution for standard SDB with various training depth data, independent of the SfM-MVS output. Experimental results in two completely different test sites in the Mediterranean and Baltic Seas demonstrate the effectiveness of the proposed approach through extensive experiments that demonstrate improvements in bathymetric accuracy, detail, coverage, and noise reduction in the predicted DSM. The code is available at this link. © 2025 The Authors

关键词： Bathymetry

Mechanistic understanding and validation of large AI models with SemanticLens

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Dreyer, Maximilian Berend, Jim Labarta, Tobias Vielhaben, Johanna Wiegand, Thomas Lapuschkin, Sebastian Samek, Wojciech Fraunhofer Heinrich Hertz Institute Germany Technische Universität Berlin Germany BIFOLD – Berlin Institute for the Foundations of Learning and Data Germany

Unlike human-engineered systems such as aeroplanes, where each component’s role and dependencies are well understood, the inner workings of AI models remain largely opaque, hindering verifiability and undermining trust. This paper introduces SEMANTICLENS, a universal explanation method for neural networks that maps hidden knowledge encoded by components (e.g., individual neurons) into the semantically structured, multimodal space of a foundation model such as CLIP. In this space, unique operations become possible, including (i) textual search to identify neurons encoding specific concepts, (ii) systematic analysis and comparison of model representations, (iii) automated labelling of neurons and explanation of their functional roles, and (iv) audits to validate decision-making against requirements. Fully scalable and operating without human input, SEMANTICLENS is shown to be effective for debugging and validation, summarizing model knowledge, aligning reasoning with expectations (e.g., adherence to the ABCDE-rule in melanoma classification), and detecting components tied to spurious correlations and their associated training data. By enabling component-level understanding and validation, the proposed approach helps bridge the "trust gap" between AI models and traditional engineered systems. We provide code for SEMANTICLENS on https://***/jim-berend/semanticlens and a demo on https://***. Copyright © 2025, The Authors. All rights reserved.

关键词：

Beyond De-Identification: A Structured Approach for Defining and Detecting Indirect Identifiers in Medical Texts

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Baroud, Ibrahim Raithel, Lisa Möller, Sebastian Roller, Roland Quality & Usability Lab Technische Universität Berlin Germany Germany BIFOLD – Berlin Institute for the Foundations of Learning and Data Germany

Sharing sensitive texts for scientific purposes requires appropriate techniques to protect the privacy of patients and healthcare personnel. Anonymizing textual data is particularly challenging due to the presence of diverse unstructured direct and indirect identifiers. To mitigate the risk of re-identification, this work introduces a schema of nine categories of indirect identifiers designed to account for different potential adversaries, including acquaintances, family members and medical staff. Using this schema, we annotate 100 MIMIC-III discharge summaries and propose baseline models for identifying indirect identifiers. We will release the annotation guidelines, annotation spans (6,199 annotations in total) and the corresponding MIMIC-III document IDs to support further research in this area. © 2025, CC BY.

关键词： Anonymity

COMMUNICATION-EFFICIENT FEDERATED learning BASED ON EXPLANATION-GUIDED PRUNING FOR REMOTE SENSING IMAGE CLASSIFICATION

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Klotz, Jonas Büyüktaş, Barış Demir, Begüm BIFOLD - Berlin Institute for the Foundations of Learning and Data Germany Faculty of Electrical Engineering and Computer Science Technische Universität Berlin Germany

Federated learning (FL) is a decentralized machine learning paradigm, where multiple clients collaboratively train a global model by exchanging only model updates with the central server without sharing the local data of clients. Due to the large volume of model updates required to be transmitted between clients and the central server, most FL systems are associated with high transfer costs (i.e., communication overhead). This issue is more critical for operational applications in remote sensing (RS), especially when large-scale RS data is processed and analyzed through FL systems with restricted communication bandwidth. To address this issue, we introduce an explanation-guided pruning strategy for communication-efficient FL in the context of RS image classification. Our pruning strategy is defined based on the layer-wise relevance propagation (LRP) driven explanations to: 1) efficiently and effectively identify the most relevant and informative model parameters (to be exchanged between clients and the central server);and 2) eliminate the non-informative ones to minimize the volume of model updates. The experimental results on the BigEarthNet-S2 dataset demonstrate that our strategy effectively reduces the number of shared model updates, while increasing the generalization ability of the global model. The code of this work will be publicly available at https://***/rsim/FL-LRP. © 2025, CC BY.

关键词： Federated learning

AttnLRP: attention-aware layer-wise relevance propagation for transformers 24

学校读者我要写书评

暂无评论

AttnLRP: attention-aware layer-wise relevance propagation fo...

Proceedings of the 41st International Conference on Machine learning

作者： Reduan Achtibat Sayed Mohammad Vakilzadeh Hatefi Maximilian Dreyer Aakriti Jain Thomas Wiegand Sebastian Lapuschkin Wojciech Samek Fraunhofer Heinrich-Hertz-Institute Berlin Germany Fraunhofer Heinrich-Hertz-Institute Berlin Germany and Technische Universität Berlin Berlin Germany and BIFOLD - Berlin Institute for the Foundations of Learning and Data Berlin Germany

Large Language Models are prone to biased predictions and hallucinations, underlining the paramount importance of understanding their model-internal reasoning process. However, achieving faithful attributions for the entirety of a black-box transformer model and maintaining computational efficiency is an unsolved challenge. By extending the Layer-wise Relevance Propagation attribution method to handle attention layers, we address these challenges effectively. While partial solutions exist, our method is the first to faithfully and holistically attribute not only input but also latent representations of transformer models with the computational efficiency similar to a single backward pass. Through extensive evaluations against existing methods on LLaMa 2, Mixtral 8×7b, Flan-T5 and vision transformer architectures, we demonstrate that our proposed approach surpasses alternative methods in terms of faithfulness and enables the understanding of latent representations, opening up the door for concept-based explanations. We provide an LRP library at https://***/rachtibat/LRP-eXplains-Transformers.

关键词：

Deep learning-based Bathymetry Retrieval without In-situ Depths using Remote Sensing Imagery and SfM-MVS DSMs with data Gaps

学校读者我要写书评

暂无评论

arXiv 2025年

关键词： Bathymetry

FITCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Qianli Feldhus, Nils Ostermann, Simon Villa-Arenas, Luis Felipe Möller, Sebastian Schmitt, Vera Germany Technische Universität Berlin Germany Saarland Informatics Campus Germany Deutsche Telekom Germany Germany BIFOLD Berlin Institute for the Foundations of Learning and Data Germany

Counterfactual examples are widely used in natural language processing (NLP) as valuable data to improve models, and in explainable artificial intelligence (XAI) to understand model behavior. The automated generation of counterfactual examples remains a challenging task even for large language models (LLMs), despite their impressive performance on many tasks. In this paper, we first introduce ZEROCF, a faithful approach for leveraging important words derived from feature attribution methods to generate counterfactual examples in a zero-shot setting. Second, we present a new framework, FITCF1, which further verifies aforementioned counterfactuals by label flip verification and then inserts them as demonstrations for few-shot prompting, outperforming two state-of-the-art baselines. Through ablation studies, we identify the importance of each of FITCF's core components in improving the quality of counterfactuals, as assessed through flip rate, perplexity, and similarity measures. Furthermore, we show the effectiveness of LIME and Integrated Gradients as backbone attribution methods for FITCF and find that the number of demonstrations has the largest effect on performance. Finally, we reveal a strong correlation between the faithfulness of feature attribution scores and the quality of generated counterfactuals. © 2025, CC BY.

关键词： Natural language processing systems

A Multi-Modal Federated learning Framework for Remote Sensing Image Classification

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Büyüktaş, Barış Sumbul, Gencer Demir, Begüm Faculty of Electrical Engineering and Computer Science Technische Universität Berlin Berlin10623 Germany BIFOLD - Berlin Institute for the Foundations of Learning and Data Berlin10623 Germany Sion1950 Switzerland

Federated learning (FL) enables the collaborative training of deep neural networks across decentralized data archives (i.e., clients) without sharing the local data of the clients. Most of the existing FL methods assume that the data distributed across all clients is associated with the same data modality. However, remote sensing (RS) images present in different clients can be associated with diverse data modalities. The joint use of the multi-modal RS data can significantly enhance classification performance. To effectively exploit decentralized and unshared multi-modal RS data, our paper introduces a novel multi-modal FL framework for RS image classification problems. The proposed framework comprises three modules: 1) multi-modal fusion (MF);2) feature whitening (FW);and 3) mutual information maximization (MIM). The MF module employs iterative model averaging to facilitate learning without accessing multi-modal training data on clients. The FW module aims to address the limitations of training data heterogeneity by aligning data distributions across clients. The MIM module aims to model mutual information by maximizing the similarity between images from different modalities. For the experimental analyses, we focus our attention on multi-label classification and pixel-based classification tasks in RS. The results obtained using two benchmark archives show the effectiveness of the proposed framework when compared to state-of-the-art algorithms in the literature. The code of the proposed framework will be available at https://***/rsim/multi-modal-FL. © 2025, CC BY.

关键词： Deep neural networks

Sparser, Better, Faster, Stronger: Efficient Automatic Differentiation for Sparse Jacobians and Hessians

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hill, Adrian Dalle, Guillaume BIFOLD - Berlin Institute for the Foundations of Learning and Data Berlin Germany Machine Learning Group Technical University of Berlin Berlin Germany LVMT ENPC Institut Polytechnique de Paris Univ Gustave Eiffel Marne-la-Vallée France

From implicit differentiation to probabilistic modeling, Jacobians and Hessians have many potential use cases in Machine learning (ML), but conventional wisdom views them as computationally prohibitive. Fortunately, these matrices often exhibit sparsity, which can be leveraged to significantly speed up the process of Automatic Differentiation (AD). This paper presents advances in Automatic Sparse Differentiation (ASD), starting with a new perspective on sparsity detection. Our refreshed exposition is based on operator overloading, able to detect both local and global sparsity patterns, and naturally avoids dead ends in the control flow graph. We also describe a novel ASD pipeline in Julia, consisting of independent software packages for sparsity detection, matrix coloring, and differentiation, which together enable ASD based on arbitrary AD backends. Our pipeline is fully automatic and requires no modification of existing code, making it compatible with existing ML codebases. We demonstrate that this pipeline unlocks Jacobian and Hessian matrices at scales where they were considered too expensive to compute. On real-world problems from scientific ML and optimization, we show significant speed-ups of up to three orders of magnitude. Notably, our ASD pipeline often outperforms standard AD for one-off computations, once thought impractical due to slower sparsity detection methods. © 2025, CC BY.

关键词： Software packages