检索结果-内蒙古大学图书馆

Sit Back and Relax: learning to Drive Incrementally in All Weather Conditions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Leitner, Stefan Mirza, M. Jehanzeb Lin, Wei Micorek, Jakub Masana, Marc Kozinski, Mateusz Possegger, Horst Bischof, Horst Institute for Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Austria Christian Doppler Laboratory for Semantic 3D Computer Vision Austria TU Graz SAL Dependable Embedded Systems Lab Silicon Austria Labs Austria

In autonomous driving scenarios, current object detection models show strong performance when tested in clear weather. However, their performance deteriorates significantly when tested in degrading weather conditions. In addition, even when adapted to perform robustly in a sequence of different weather conditions, they are often unable to perform well in all of them and suffer from catastrophic forgetting. To efficiently mitigate forgetting, we propose Domain-Incremental learning through Activation Matching (DILAM), which employs unsupervised feature alignment to adapt only the affine parameters of a clear weather pre-trained network to different weather conditions. We propose to store these affine parameters as a memory bank for each weather condition and plug-in their weather-specific parameters during driving (i.e. test time) when the respective weather conditions are encountered. Our memory bank is extremely lightweight, since affine parameters account for less than 2% of a typical object detector. Furthermore, contrary to previous domain-incremental learning approaches, we do not require the weather label when testing and propose to automatically infer the weather condition by a majority voting linear classifier. © 2023, CC BY.

关键词： Object detection

ActMAD: Activation Matching to Align Distributions for Test-Time-Training

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mirza, Muhammad Jehanzeb Soneira, Pol Jané Lin, Wei Kozinski, Mateusz Possegger, Horst Bischof, Horst Institute for Computer Graphics and Vision TU Graz Austria Christian Doppler Laboratory for Embedded Machine Learning Institute of Control Systems KIT Germany Christian Doppler Laboratory for Semantic 3D Computer Vision

Test-Time-Training (TTT) is an approach to cope with out-of-distribution (OOD) data by adapting a trained model to distribution shifts occurring at test-time. We propose to perform this adaptation via Activation Matching (ActMAD): We analyze activations of the model and align activation statistics of the OOD test data to those of the training data. In contrast to existing methods, which model the distribution of entire channels in the ultimate layer of the feature extractor, we model the distribution of each feature in multiple layers across the network. This results in a more fine-grained supervision and makes ActMAD attain state of the art performance on CIFAR-100C and Imagenet-C. ActMAD is also architecture- and task-agnostic, which lets us go beyond image classification, and score 15.4% improvement over previous approaches when evaluating a KITTI-trained object detector on KITTI-Fog. Our experiments highlight that ActMAD can be applied to online adaptation in realistic scenarios, requiring little data to attain its full performance. © 2022, CC BY.

关键词： Chemical activation

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

IEEE Transactions on Pattern Analysis and machine Intelligence 2025年第7期47卷 5901-5917页

作者： Shujian Yu Hongming Li Sigurd Løkse Robert Jenssen José C. Príncipe Machine Learning Group UiT - The Arctic University of Norway Tromsø Norway Quantitative Data Analytics Group Vrije Universiteit Amsterdam Amsterdam The Netherlands Department of Electrical and Computer Engineering University of Florida Gainesville FL USA Drones and Autonomous Systems Group NORCE Norwegian Research Centre Tromsø Norway Pioneer AI Centre Copenhagen University København Denmark 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 elegantly 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 Kullback-Leibler 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.

关键词： Covariance matrices Kernel machine learning Time series analysis Vectors Symmetric matrices Q measurement Matrix decomposition Estimation Decision making

RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement

学校读者我要写书评

暂无评论

RecycleNet: Latent Feature Recycling Leads to Iterative Deci...

IEEE Workshop on Applications of computer vision (WACV)

作者： Gregor Koehler Tassilo Wald Constantin Ulrich David Zimmerer Paul F. Jaeger Jörg K. H. Franke Simon Kohl Fabian Isensee Klaus H. Maier-Hein Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Helmholtz Information and Data Science School for Health Karlsruhe/Heidelberg Germany Helmholtz Imaging DKFZ National Center for Tumor Diseases (NCT) NCT Heidelberg a Partnership Between DKFZ University Medical Center Heidelberg Interactive Machine Learning Group DKFZ Machine Learning Lab University of Freiburg Freiburg Germany Latent Labs (***) London UK Applied Computer Vision Lab DKFZ Pattern Analysis and Learning Group Heidelberg University Hospital Heidelberg Germany

Despite the remarkable success of deep learning systems over the last decade, a key difference still remains between neural network and human decision-making: As humans, we can not only form a decision on the spot, but also ponder, revisiting an initial guess from different angles, distilling relevant information, arriving at a better decision. Here, we propose RecycleNet, a latent feature recycling method, instilling the pondering capability for neural networks to refine initial decisions over a number of recycling steps, where outputs are fed back into earlier network layers in an iterative fashion. This approach makes minimal assumptions about the neural network architecture and thus can be implemented in a wide variety of contexts. Using medical image segmentation as the evaluation environment, we show that latent feature recycling enables the network to iteratively refine initial predictions even beyond the iterations seen during training, converging towards an improved decision. We evaluate this across a variety of segmentation benchmarks and show consistent improvements even compared with top-performing segmentation methods. This allows trading increased computation time for improved performance, which can be beneficial, especially for safety-critical applications.

关键词：

RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Koehler, Gregor Wald, Tassilo Ulrich, Constantin Zimmerer, David Jaeger, Paul F. Franke, Jörg K.H. Kohl, Simon Isensee, Fabian Maier-Hein, Klaus H. Heidelberg Division of Medical Image Computing Germany Helmholtz Information and Data Science School for Health Karlsruhe Heidelberg Germany Helmholtz Imaging DKFZ Germany NCT Heidelberg a partnership between DKFZ University Medical Center Heidelberg Germany Interactive Machine Learning Group DKFZ Applied Computer Vision Lab DKFZ Machine Learning Lab University of Freiburg Freiburg Germany London United Kingdom Pattern Analysis and Learning Group Heidelberg University Hospital Heidelberg Germany

关键词： Network layers

VICE: variational interpretable concept embeddings 22

学校读者我要写书评

暂无评论

VICE: variational interpretable concept embeddings

Proceedings of the 36th International Conference on Neural Information Processing systems

作者： Lukas Muttenthaler Charles Y. Zheng Patrick McClure Robert A. Vandermeulen Martin N. Hebart Francisco Pereira Machine Learning Group Technische Universität Berlin Berlin Institute for the Foundations of Learning and Data (BIFOLD) Berlin Germany Machine Learning Team FMRI Facility National Institute of Mental Health Bethesda MD Department of Computer Science Naval Postgraduate School Monterey CA Vision and Computational Cognition Group MPI for Human Cognitive and Brain Sciences Leipzig Germany

ISBN: (纸本)9781713871088

A central goal in the cognitive sciences is the development of numerical models for mental representations of object concepts. This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for embedding object concepts in a vector space using data collected from humans in a triplet odd-one-out task. VICE uses variational inference to obtain sparse, non-negative representations of object concepts with uncertainty estimates for the embedding values. These estimates are used to automatically select the dimensions that best explain the data. We derive a PAC learning bound for VICE that can be used to estimate generalization performance or determine a sufficient sample size for experimental design. VICE rivals or outperforms its predecessor, SPoSE, at predicting human behavior in the triplet odd-one-out task. Furthermore, VICE's object representations are more reproducible and consistent across random initializations, highlighting the unique advantage of using VICE for deriving interpretable embeddings from human behavior.

关键词：

Reproducibility and Geometric Intrinsic Dimensionality: An Investigation on Graph Neural Network Research

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hille, Tobias Stubbemann, Maximilian Hanika, Tom Knowledge & Data Engineering Group University of Kassel Kassel Germany Interdisciplinary Research Center for Information System Design University of Kassel Kassel Germany Information Systems and Machine Learning Lab University of Hildesheim Hildesheim Germany Institute of Computer Science University of Hildesheim Hildesheim Germany

Difficulties in replication and reproducibility of empirical evidences in machine learning research have become a prominent topic in recent years. Ensuring that machine learning research results are sound and reliable requires reproducibility, which verifies the reliability of research findings using the same code and data. This promotes open and accessible research, robust experimental workflows, and the rapid integration of new findings. Evaluating the degree to which research publications support these different aspects of reproducibility is one goal of the present work. For this we introduce an ontology of reproducibility in machine learning and apply it to methods for graph neural networks. Building on these efforts we turn towards another critical challenge in machine learning, namely the curse of dimensionality, which poses challenges in data collection, representation, and analysis, making it harder to find representative data and impeding the training and inference processes. Using the closely linked concept of geometric intrinsic dimension we investigate to which extend the used machine learning models are influenced by the intrinsic dimension of the data sets they are trained *** Codes 68T01 68T07 68T09 51F99 Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

Pattern Discovery in an EEG Database of Depression Patients: Preliminary Results

学校读者我要写书评

暂无评论

Pattern Discovery in an EEG Database of Depression Patients:...

International Conference on Measurement

作者： Kateřina Hlaváčková-Schindler Christina Pacher Claudia Plant Mykola Lazarenko Milan Paluš Jaroslav Hlinka Aditi Kathpalia Martin Brunovský Data Mining and Machine Learning Research Group Faculty of Computer Science University of Vienna Vienna Austria Department of Complex Systems Institute of Computer Science Czech Academy of Sciences Prague Czechia Clinical Research Programme National Institute of Mental Health Klecany Czechia

The ability to predict response to medication treatment of depressed patients, either early in the course of therapy or before treatment even begins can avoid trials of ineffective therapy and save patients from prolonged intervals of suffering. Symptom alleviation requires 4-6 weeks after starting current antidepressive medication. Based on the data basis of the patients and their EEG before and on the 7th day of treatment we apply data mining, causal discovery and machine learning approaches to discover interactive patterns between patient’s brain regions to separate the treatment responders from non-responders. In this paper we report the preliminary results of our international project "learning Synchronization Patterns in Multivariate Neural Signals for Prediction of Response to Antidepressants" ongoing at the University of Vienna, the Czech Academy of Sciences and the National Institute of Mental Health in the Czech Republic.

关键词：

Semi-supervised Classification of Malware Families Under Extreme Class Imbalance via Hierarchical Non-Negative Matrix Factorization with Automatic Model Selection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Eren, Maksim E. Bhattarai, Manish Joyce, Robert J. Raff, Edward Nicholas, Charles Alexandrov, Boian S. Advanced Research in Cyber Systems LANL United States Theoretical Division LANL United States Machine Learning Research Group Booz Allen Hamilton United States Department of Computer Science and Electrical Engineering UMBC United States

Identification of the family to which a malware specimen belongs is essential in understanding the behavior of the malware and developing mitigation strategies. Solutions proposed by prior work, however, are often not practicable due to the lack of realistic evaluation factors. These factors include learning under class imbalance, the ability to identify new malware, and the cost of production-quality labeled data. In practice, deployed models face prominent, rare, and new malware families. At the same time, obtaining a large quantity of up-to-date labeled malware for training a model can be expensive. In this paper, we address these problems and propose a novel hierarchical semi-supervised algorithm, which we call the HNMFk Classifier, that can be used in the early stages of the malware family labeling process. Our method is based on non-negative matrix factorization with automatic model selection, that is, with an estimation of the number of clusters. With HNMFk Classifier, we exploit the hierarchical structure of the malware data together with a semi-supervised setup, which enables us to classify malware families under conditions of extreme class imbalance. Our solution can perform abstaining predictions, or rejection option, which yields promising results in the identification of novel malware families and helps with maintaining the performance of the model when a low quantity of labeled data is used. We perform bulk classification of nearly 2,900 both rare and prominent malware families, through static analysis, using nearly 388,000 samples from the EMBER-2018 corpus. In our experiments, we surpass both supervised and semi-supervised baseline models with an F1 score of 0.80. Copyright © 2023, The Authors. All rights reserved.

关键词： Non-negative matrix factorization