检索结果-内蒙古大学图书馆

An Efficient Domain-Incremental learning Approach to Drive in All Weather Conditions

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mirza, Muhammad Jehanzeb Masana, Marc Possegger, Horst Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Austria TU Graz SAL Dependable Embedded Systems Lab Silicon Austria Labs Austria

Although deep neural networks enable impressive visual perception performance for autonomous driving, their robustness to varying weather conditions still requires attention. When adapting these models for changed environments, such as different weather conditions, they are prone to forgetting previously learned information. This catastrophic forgetting is typically addressed via incremental learning approaches which usually re-train the model by either keeping a memory bank of training samples or keeping a copy of the entire model or model parameters for each scenario. While these approaches show impressive results, they can be prone to scalability issues and their applicability for autonomous driving in all weather conditions has not been shown. In this paper we propose DISC - Domain Incremental through Statistical Correction - a simple online zero-forgetting approach which can incrementally learn new tasks (i.e. weather conditions) without requiring re-training or expensive memory banks. The only information we store for each task are the statistical parameters as we categorize each domain by the change in first and second order statistics. Thus, as each task arrives, we simply 'plug and play' the statistical vectors for the corresponding task into the model and it immediately starts to perform well on that task. We show the efficacy of our approach by testing it for object detection in a challenging domain-incremental autonomous driving scenario where we encounter different adverse weather conditions, such as heavy rain, fog, and snow. © 2022, CC BY.

关键词： Meteorology

Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Marinov, Zdravko Jäger, Paul F. Egger, Jan Kleesiek, Jens Stiefelhagen, Rainer The Computer Vision for Human-Computer Interaction Lab Department of Informatics Karlsruhe Institute of Technology Adenauerring 10 Karlsruhe76131 Germany Girardetstraße 2 Essen45131 Germany Heidelberg Interactive Machine Learning Group Im Neuenheimer Feld 223 Heidelberg69120 Germany The Helmholtz Imaging DKFZ Im Neuenheimer Feld 223 Heidelberg69120 Germany

Interactive segmentation is a crucial research area in medical image analysis aiming to boost the efficiency of costly annotations by incorporating human feedback. This feedback takes the form of clicks, scribbles, or masks and allows for iterative refinement of the model output so as to efficiently guide the system towards the desired behavior. In recent years, deep learning-based approaches have propelled results to a new level causing a rapid growth in the field with 121 methods proposed in the medical imaging domain alone. In this review, we provide a structured overview of this emerging field featuring a comprehensive taxonomy, a systematic review of existing methods, and an in-depth analysis of current practices. Based on these contributions, we discuss the challenges and opportunities in the field. For instance, we find that there is a severe lack of comparison across methods which needs to be tackled by standardized baselines and benchmarks. Appendixes are here. © 2023, CC BY.

关键词： Medical imaging

Non-Invasive Diagnosis of Nutrient Deficiencies in Winter Wheat and Winter Rye Using Uav-Based Rgb Images

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Yi, Jinhui Lopez, Gina Hadir, Sofia Weyler, Jan Klingbeil, Lasse Deichmann, Marion Gall, Juergen Seidel, Sabine J. University of Bonn Computer Vision Group Institute of Computer Science Friedrich-Hirzebruch-Allee 8 Bonn53115 Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany University of Bonn Crop Science Group INRES Katzenburgweg 5 Bonn53115 Germany University of Bonn Institute of Geodesy and Geoinformation Nußallee 17 Bonn53115 Germany University of Bonn Plant Nutrition Group INRES Karlrobert-Kreiten-Strasse 13 Bonn53115 Germany

Better matching of the timing and amount of fertilizer inputs to plant requirements will improve nutrient use efficiency and crop yields and could reduce negative environmental impacts. Deep learning can be a powerful digital tool for on-site real-time non-invasive diagnosis of crop nutrient deficiencies. A drone-based RGB image dataset was generated together with ground truthing data in winter wheat (2020) and in winter rye (2021) during tillering and booting in the long-term fertilizer experiment (LTFE) Dikopshof. In this LTFE, the crops are fertilized with the same amounts since decades. The selected treatments include full fertilization including manure (NPKCa+m+s), mineral fertilization (NPKCa), mineral fertilization but no nitrogen (N) application (_PKCa), no phosphorous (P) application (N_KCa), no potassium (K) application (NP_Ca), or no liming (Ca) (NPK_), as well as an unfertilized treatment. The image dataset consisting of more than 3600 UAV-based RGB images was used to train and evaluate in total eight CNN-based and transformerbased models as baselines within each crop-year and across the two crop-year combinations aiming to detect the specific fertilizer treatments including the specific nutrient deficiencies. The field observations show a strong biomass decline in the case of N omission and no fertilization though the effects are lower in the case of P, K, and lime omission. The mean detection accuracy within one year was 75% (winter wheat) and 81% (winter rye) across models and treatments. Hereby, the detection accuracy for winter wheat was highest for the NPKCa+m+s (100%) and the unfertilized (96%) treatments as well as the _PKCa treatment (92%), whereas for treatments N_KCa and NPKCa the accuracy was lowest (about 50%). The results were similar for winter rye. In the cross-year and cross-cereal species transfer (training on winter wheat, application on winter rye, and vice versa) the mean accuracy was about 18%. The results highlight the potential of

关键词： Crops

Latent Event-Predictive Encodings through Counterfactual Regularization 43

学校读者我要写书评

暂无评论

Latent Event-Predictive Encodings through Counterfactual Reg...

43rd Annual Meeting of the Cognitive Science Society: Comparative Cognition: Animal Minds, CogSci 2021

作者： Humaidan, Dania Otte, Sebastian Gumbsch, Christian Wu, Charley Butz, Martin V. Neuro-Cognitive Modeling Group Dep. of Psychology Dep. of Computer Science Sand 14 Tübingen72076 Germany Cluster of Excellence – Machine Learning for Science Maria-von-Linden-Str. 6 Tübingen72076 Germany Autonomous Learning Group MPI for Intelligent Systems Tübingen72076 Germany Human and Machine Cognition Lab Maria-von-Linden-Str. 6 Tübingen72076 Germany

A critical challenge for any intelligent system is to infer structure from continuous data streams. Theories of event-predictive cognition suggest that the brain segments sensorimotor information into compact event encodings, which are used to anticipate and interpret environmental dynamics. Here, we introduce a SUrprise-GAted Recurrent neural network (SUGAR) using a novel form of counterfactual regularization. We test the model on a hierarchical sequence prediction task, where sequences are generated by alternating hidden graph structures. Our model learns to both compress the temporal dynamics of the task into latent event-predictive encodings and anticipate event transitions at the right moments, given noisy hidden signals about them. The addition of the counterfactual regularization term ensures fluid transitions from one latent code to the next, whereby the resulting latent codes exhibit compositional properties. The implemented mechanisms offer a host of useful applications in other domains, including hierarchical reasoning, planning, and decision making. © Cognitive Science Society: Comparative Cognition: Animal Minds, CogSci *** rights reserved.

关键词： Intelligent systems

Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Haopeng Deng, Andong Liu, Jun Rahmani, Hossein Guo, Yulan Schiele, Bernt Bennamoun, Mohammed Ke, Qiuhong School of Computing and Information Systems University of Melbourne Australia Center for Research in Computer Vision University of Central Florida United States Pillar Singapore University of Technology and Design Singapore School of Computing and Communications Lancaster University United Kingdom School of Electronics and Communication Engineering Sun Yat-sen University China Department of Computer Vision and Machine Learning Max Planck Institute for Informatics Saarland Informatics Campus Germany School of Physics Maths and Computing University of Western Australia Australia Department of Data Science & AI Monash University Australia

Reasoning over sports videos for question answering is an important task with numerous applications, such as player training and information retrieval. However, this task has not been explored due to the lack of relevant datasets and the challenging nature it presents. Most datasets for video question answering (VideoQA) focus mainly on general and coarse-grained understanding of daily-life videos, which is not applicable to sports scenarios requiring professional action understanding and fine-grained motion analysis. In this paper, we introduce the first dataset, named Sports-QA, specifically designed for the sports VideoQA task. The Sports-QA dataset includes various types of questions, such as descriptions, chronologies, causalities, and counterfactual conditions, covering multiple sports. Furthermore, to address the characteristics of the sports VideoQA task, we propose a new Auto-Focus Transformer (AFT) capable of automatically focusing on particular scales of temporal information for question answering. We conduct extensive experiments on Sports-QA, including baseline studies and the evaluation of different methods. The results demonstrate that our AFT achieves state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Question answering

Capacitor Minimization in Analog Synapses for Efficient and Compact Binarized SNNs

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems for Artificial Int...

IEEE Transactions on Circuits and systems for Artificial Intelligence 2025年第2期2卷 114-125页

作者： Mikail Yayla Ming-Liang Wei Simon Thomann Albi Mema Chia-Lin Yang Jian-Jia Chen Hussam Amrouch Design Automation for Embedded Systems Group TU Dortmund University Dortmund Germany Lamarr Institute for Machine Learning and Artificial Intelligence Dortmund Germany Department of the Graduate Institute of Electronics Engineering National Taiwan University Taipei Taiwan Technical University of Munich (TUM) Munich Germany TUM School of Computation Information and Technology Chair of AI Processor Design Munich Institute of Robotics and Machine Intelligence Munich Germany Department of Computer Science and Information Engineering Graduate Institute of Electronics Engineering National Taiwan University Taipei Taiwan Department of Computer Science TU Dortmund University Dortmund Germany Lamarr Institute Dortmund Germany

Accelerating the immense workloads of Neural Networks (NNs) is a critical challenge, and analog computing-based approaches present a promising solution. Among these, the Integrate-and-Fire (IF) Spiking Neural Network (SNN) stands out for its potential in efficient neural computation. However, achieving high inference accuracy through precise multiply-accumulate (MAC) operations necessitates a large membrane capacitor—224 to 547 times larger than the synapse array at the 14nm technology node—resulting in prohibitive area costs. Additionally, the large capacitor size introduces higher energy consumption and longer access times. Thus, a key research challenge is maintaining accuracy while mitigating the costs associated with the large membrane capacitor. In this work, we propose a HW/SW Codesign method, called CapMin, for capacitor size minimization in analog computing IF-SNNs. CapMin minimizes the capacitor size by reducing the number of spike times needed for accurate operation of the HW, based on the absolute frequency of MAC level occurrences in the SW. To increase the operation of IF-SNNs to current variation, we propose the method CapMin-V, which trades capacitor size for protection based on the reduced capacitor size found in CapMin. In our experiments, CapMin achieves more than a 14 $\times$ reduction in capacitor size along with a 34% reduction in energy consumption over the state of the art, while CapMin-V achieves increased variation tolerance in the IF-SNN operation, requiring only a small increase in capacitor size.

关键词： Capacitors Circuits Accuracy Capacitance Micromechanical devices Costs Neurons Integrated circuit modeling Spiking neural networks Hardware

Long-Horizon Multi-Robot Rearrangement Planning for Construction Assembly

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hartmann, Valentin N. Orthey, Andreas Driess, Danny Oguz, Ozgur S. Toussaint, Marc Machine Learning & Robotics Lab University of Stuttgart Germany Learning and Intelligent Systems Group TU Berlin Germany Department of Computer Engineering Bilkent University Turkey

Robotic assembly planning enables architects to explicitly account for the assembly process during the design phase, and enables efficient building methods that profit from the robots' different capabilities. Previous work has addressed planning of robot assembly sequences and identifying the feasibility of architectural designs. This paper extends previous work by enabling planning with large, heterogeneous teams of robots. We present a planning system which enables parallelization of complex task and motion planning problems by iteratively solving smaller subproblems. Combining optimization methods to solve for manipulation constraints with a sampling-based bi-directional space-time path planner enables us to plan cooperative multirobot manipulation with unknown arrival-times. Thus, our solver allows for completing subproblems and tasks with differing timescales and synchronizes them effectively. We demonstrate the approach on multiple case-studies to show the robustness over long planning horizons and scalability to many objects and agents of our algorithm. Finally, we also demonstrate the execution of the computed plans on two robot arms to showcase the feasibility in the real world. Copyright © 2021, The Authors. All rights reserved.

关键词： Robotics

Overcoming common flaws in the evaluation of selective classification systems 24

学校读者我要写书评

暂无评论

Overcoming common flaws in the evaluation of selective class...

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Jeremias Traub Till J. Bungert Carsten T. Lüth Michael Baumgartner Klaus H. Maier-Hein Lena Maier-Hein Paul F. Jäger German Cancer Research Center (DKFZ) Heidelberg Interactive Machine Learning Group Germany and Helmholtz Imaging DKFZ Heidelberg Germany German Cancer Research Center (DKFZ) Heidelberg Interactive Machine Learning Group Germany and Helmholtz Imaging DKFZ Heidelberg Germany and Faculty of Mathematics and Computer Science University of Heidelberg Germany Helmholtz Imaging DKFZ Heidelberg Germany and DKFZ Heidelberg Division of Medical Image Computing (MIC) Germany and Faculty of Mathematics and Computer Science University of Heidelberg Germany Helmholtz Imaging DKFZ Heidelberg Germany and DKFZ Heidelberg Division of Medical Image Computing (MIC) Germany and Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Heidelberg Germany and Faculty of Mathematics and Computer Science University of Heidelberg Germany and National Center for Tumor Diseases (NCT) Heidelberg Helmholtz Imaging DKFZ Heidelberg Germany and DKFZ Heidelberg Division of Intelligent Medical Systems (IMSY) Germany and Faculty of Mathematics and Computer Science University of Heidelberg Germany and National Center for Tumor Diseases (NCT) Heidelberg

ISBN: (纸本)9798331314385

Selective Classification, wherein models can reject low-confidence predictions, promises reliable translation of machine-learning based classification systems to real-world scenarios such as clinical diagnostics. While current evaluation of these systems typically assumes fixed working points based on pre-defined rejection thresholds, methodological progress requires benchmarking the general performance of systems akin to the AUROC in standard classification. In this work, we define 5 requirements for multi-threshold metrics in selective classification regarding task alignment, interpretability, and flexibility, and show how current approaches fail to meet them. We propose the Area under the Generalized Risk Coverage curve (AUGRC), which meets all requirements and can be directly interpreted as the average risk of undetected failures. We empirically demonstrate the relevance of AUGRC on a comprehensive benchmark spanning 6 data sets and 13 confidence scoring functions. We find that the proposed metric substantially changes metric rankings on 5 out of the 6 data sets.

关键词：

The Conditional Cauchy-Schwarz Divergence with Applications to Time-Series Data and Sequential Decision Making

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yu, Shujian Li, Hongming Løkse, Sigurd Jenssen, Robert Príncipe, José C. The Machine Learning Group UiT - The Arctic University of Norway Tromsø Norway The Quantitative Data Analytics Group Vrije Universiteit Amsterdam Netherlands The Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States The Drones and Autonomous Systems group at NORCE Norwegian Research Centre Tromsø Norway The Pioneer AI Centre Copenhagen University The Norwegian Computing Center Oslo Norway

The Cauchy-Schwarz (CS) divergence was developed by Príncipe et al. in 2000. In this paper, we extend the classic CS divergence to quantify the closeness between two conditional distributions and show that the developed conditional CS divergence can be simply estimated by a kernel density estimator from given samples. We illustrate the advantages (e.g., rigorous faithfulness guarantee, lower computational complexity, higher statistical power, and much more flexibility in a wide range of applications) of our conditional CS divergence over previous proposals, such as the conditional KL divergence and the conditional maximum mean discrepancy. We also demonstrate the compelling performance of conditional CS divergence in two machine learning tasks related to time series data and sequential inference, namely time series clustering and uncertainty-guided exploration for sequential decision making. Copyright © 2023, The Authors. All rights reserved.

关键词： machine learning