检索结果-内蒙古大学图书馆

CVPR19 Tracking and Detection Challenge: How crowded can it get?

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Dendorfer, Patrick Rezatofighi, Hamid Milan, Anton Shi, Javen Cremers, Daniel Reid, Ian Roth, Stefan Schindler, Konrad Leal-Taixa, Laura Dynamic Vision and Learning Group at Tum Munich Germany Australian Institute for Machine Learning and School of Computer Science at University of Adelaide. Amazon Berlin Germany Photogrammetry and Remote Sensing Group at Eth Zurich Switzerland Computer Vision Group at Tum Munich Germany Department of Computer Science Technische Universität Darmstadt Germany

Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide the most objective measure of performance and are therefore important guides for research. The benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal to establish a standardized evaluation of multiple object tracking methods. The challenge focuses on multiple people tracking, since pedestrians are well studied in the tracking community, and precise tracking and detection has high practical relevance. Since the first release, MOT15 [5], MOT16 [8], and MOT17 [8] have tremendously contributed to the community by introducing a clean dataset and precise framework to benchmark multi-object trackers. In this paper, we present our CVPR19 benchmark, consisting of 8 new sequences depicting very crowded challenging scenes. The benchmark will be presented at the 4th BMTT MOT Challenge Workshop at the computer vision and Pattern Recognition Conference (CVPR) 2019, and will evaluate the state-of-the-art in multiple object tracking whend handling extremely crowded scenarios. Copyright © 2019, The Authors. All rights reserved.

关键词： computer vision

Feature relevance bounds for ordinal regression

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Pfannschmidt, Lukas Jakob, Jonathan Biehl, Michael Tino, Peter Hammer, Barbara Machine Learning Group Bielefeld University Germany Intelligent Systems Group University of Groningen Netherlands Computer Science University of Birmingham United Kingdom

The increasing occurrence of ordinal data, mainly sociodemographic, led to a renewed research interest in ordinal regression, i.e. the prediction of ordered classes. Besides model accuracy, the interpretation of these models itself is of high relevance, and existing approaches therefore enforce e.g. model sparsity. For high dimensional or highly correlated data, however, this might be misleading due to strong variable dependencies. In this contribution, we aim for an identification of feature relevance bounds which - besides identifying all relevant features - explicitly differentiates between strongly and weakly relevant features. Copyright © 2019, The Authors. All rights reserved.

关键词： machine learning

Multi-label Classification with High-rank and High-order Label Correlations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Si, Chongjie Jia, Yuheng Wang, Ran Zhang, Min-Ling Feng, Yanghe Qu, Chongxiao The Chien-Shiung Wu College Southeast University Nanjing210096 China The MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China The School of Computer Science and Engineering Southeast University Nanjing210096 China Ministry of Education China School of Computing & Information Sciences Caritas Institute of Higher Education Hong Kong The Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China The School of Mathematical Science Shenzhen University Shenzhen518060 China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen518060 China The College of Systems Engineering National University of Defense Technology China The 52nd Research Institute of China Electronics Technology Group China

Exploiting label correlations is important to multi-label classification. Previous methods capture the high-order label correlations mainly by transforming the label matrix to a latent label space with low-rank matrix factorization. However, the label matrix is generally a full-rank or approximate full-rank matrix, making the low-rank factorization inappropriate. Besides, in the latent space, the label correlations will become implicit. To this end, we propose a simple yet effective method to depict the high-order label correlations explicitly, and at the same time maintain the high-rank of the label matrix. Moreover, we estimate the label correlations and infer model parameters simultaneously via the local geometric structure of the input to achieve mutual enhancement. Comparative studies over twelve benchmark data sets validate the effectiveness of the proposed algorithm in multi-label classification. The exploited high-order label correlations are consistent with common sense empirically. Our code is publicly available at https://***/Chongjie-Si/HOMI. Copyright © 2022, The Authors. All rights reserved.

关键词： Matrix algebra

Feature relevance determination for ordinal regression in the context of feature redundancies and privileged information

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Pfannschmidta, Lukas Jakob, Jonathan Hinder, Fabian Biehl, Michael Tino, Peter Hammer, Barbara Machine Learning Group Bielefeld University DE Germany Intelligent Systems Group University of Groningen NL Computer Science University of Birmingham United Kingdom

Advances in machine learning technologies have led to increasingly powerful models in particular in the context of big data. Yet, many application scenarios demand for robustly interpretable models rather than optimum model accuracy;as an example, this is the case if potential biomarkers or causal factors should be discovered based on a set of given measurements. In this contribution, we focus on feature selection paradigms, which enable us to uncover relevant factors of a given regularity based on a sparse model. We focus on the important specific setting of linear ordinal regression, i.e. data have to be ranked into one of a finite number of ordered categories by a linear projection. Unlike previous work, we consider the case that features are potentially redundant, such that no unique minimum set of relevant features exists. We aim for an identification of all strongly and all weakly relevant features as well as their type of relevance (strong or weak);we achieve this goal by determining feature relevance bounds, which correspond to the minimum and maximum feature relevance, respectively, if searched over all equivalent models. In addition, we discuss how this setting enables us to substitute some of the features, e.g. due to their semantics, and how to extend the framework of feature relevance intervals to the setting of privileged information, i.e. potentially relevant information is available for training purposes only, but cannot be used for the prediction itself. Copyright © 2019, The Authors. All rights reserved.

关键词： Feature extraction

Fuel consumption analysis of driven trips with respect to route choice

学校读者我要写书评

暂无评论

Fuel consumption analysis of driven trips with respect to ro...

International Conference on Data Engineering Workshops

作者： Ekaterina Gilman Satu Tamminen Anja Keskinarkaus Theodoros Anagnostopoulos Xiang Su Susanna Pirttikangas Jukka Riekki Center for Ubiquitous Computing University of Oulu Finland Biomimetics and Intelligent Systems Group University of Oulu Finland Center for Machine Vision and Signal Analysis University of Oulu Finland Department of Infocommunication Technologies ITMO University Saint Petersburg Russia Department of Computer Science University of Helsinki Finland

ISBN: (数字)9781728142661

ISBN: (纸本)9781728142678

Advances in technology equip traffic domain with instruments to gather and analyse data for safe and fuel-efficient traveling. In this article, we elaborate on the effects that taxi drivers' route selection has on fuel efficiency. For this purpose, we fuse real driving behaviour data from taxi cabs, weather, digital map, and traffic situation information to gain understanding of how the routes are selected and what are the effects in terms of fuel-efficiency. Analysis of actually driven trips and their quickest and shortest counterparts is conducted to find out the fuel-efficiency consequences on route selection. The judgments are used for developing a fuel-consumption model, exploring further the route characteristics and external factors affecting fuel consumption.

关键词： Roads Fuels Public transportation Vehicles Meteorology Meters Fuses

Confidence intervals uncovered: Are we ready for real-world medical imaging AI?

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Christodoulou, Evangelia Reinke, Annika Houhou, Rola Kalinowski, Piotr Erkan, Selen Sudre, Carole H. Burgos, Ninon Boutaj, Sofiène Loizillon, Sophie Solal, Maëlys Rieke, Nicola Cheplygina, Veronika Antonelli, Michela Mayer, Leon D. Tizabi, Minu D. Jorge Cardoso, M. Simpson, Amber Jäger, Paul F. Kopp-Schneider, Annette Varoquaux, Gaël Colliot, Olivier Maier-Hein, Lena Heidelberg Div. Intelligent Medical Systems Germany AI Health Innovation Cluster Germany NCT Heidelberg a partnership between DKFZ Heidelberg University Hospital Germany DKFZ Heidelberg Helmholtz Imaging Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Germany DKFZ Heidelberg Interactive Machine Learning Group Germany MRC Unit for Lifelong Health and Ageing UCL Centre for Medical Image Computing Department of Computer Science University College London United Kingdom School of Biomedical Engineering and Imaging Science King’s College London United Kingdom Sorbonne Université Institut du Cerveau - Paris Brain Institute - ICM CNRS Inria Inserm AP-HP Hôpital de la Pitié-Salpêtrière France NVIDIA Germany Department of Computer Science IT University of Copenhagen Denmark Centre for Medical Image Computing University College London United Kingdom School of Computing Queen’s University Canada Department of Biomedical and Molecular Sciences Queen’s University Canada Division of Biostatistics DKFZ Germany Parietal project team INRIA Saclay-Île de France France Faculty of Mathematics and Computer Science Heidelberg University Germany Medical Faculty Heidelberg University Germany

Medical imaging is spearheading the AI transformation of healthcare. Performance reporting is key to determine which methods should be translated into clinical practice. Frequently, broad conclusions are simply derived from mean performance values. In this paper, we argue that this common practice is often a misleading simplification as it ignores performance variability. Our contribution is threefold. (1) Analyzing all MICCAI segmentation papers (n = 221) published in 2023, we first observe that more than 50% of papers do not assess performance variability at all. Moreover, only one (0.5%) paper reported confidence intervals (CIs) for model performance. (2) To address the reporting bottleneck, we show that the unreported standard deviation (SD) in segmentation papers can be approximated by a second-order polynomial function of the mean Dice similarity coefficient (DSC). Based on external validation data from 56 previous MICCAI challenges, we demonstrate that this approximation can accurately reconstruct the CI of a method using information provided in publications. (3) Finally, we reconstructed 95% CIs around the mean DSC of MICCAI 2023 segmentation papers. The median CI width was 0.03 which is three times larger than the median performance gap between the first and second ranked method. For more than 60% of papers, the mean performance of the second-ranked method was within the CI of the first-ranked method. We conclude that current publications typically do not provide sufficient evidence to support which models could potentially be translated into clinical practice. © 2024, CC BY.

关键词： Medical imaging

Continuous-time deep glioma growth models

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Petersen, Jens Isensee, Fabian Köhler, Gregor Jäger, Paul F. Zimmerer, David Neuberger, Ulf Wick, Wolfgang Debus, Jürgen Heiland, Sabine Bendszus, Martin Vollmuth, Philipp Maier-Hein, Klaus H. Division of Medical Image Computing German Cancer Research Center Heidelberg Germany HIP Applied Computer Vision Lab Division of Medical Image Computing German Cancer Research Center Germany Interactive Machine Learning Group German Cancer Research Center Germany Department of Neuroradiology Heidelberg University Hospital Heidelberg Germany Neurology Clinic Heidelberg University Hospital Germany DKTK CCU Neurooncology German Cancer Research Center Germany Heidelberg Germany Heidelberg University Hospital Germany Clinical Cooperation Unit Radiation Oncology German Cancer Research Center Germany

The ability to estimate how a tumor might evolve in the future could have tremendous clinical benefits, from improved treatment decisions to better dose distribution in radiation therapy. Recent work has approached the glioma growth modeling problem via deep learning and variational inference, thus learning growth dynamics entirely from a real patient data distribution. So far, this approach was constrained to predefined image acquisition intervals and sequences of fixed length, which limits its applicability in more realistic scenarios. We overcome these limitations by extending Neural Processes, a class of conditional generative models for stochastic time series, with a hierarchical multi-scale representation encoding including a spatio-temporal attention mechanism. The result is a learned growth model that can be conditioned on an arbitrary number of observations, and that can produce a distribution of temporally consistent growth trajectories on a continuous time axis. On a dataset of 379 patients, the approach successfully captures both global and finer-grained variations in the images, exhibiting superior performance compared to other learned growth models. © 2021, CC BY-SA.

关键词： Tumors

Towards robust partially supervised multi-structure medical image segmentation on small-scale data

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Dong, Nanqing Kampffmeyer, Michael Liang, Xiaodan Xu, Min Voiculescu, Irina Xing, Eric Department of Computer Science University of Oxford Oxford United Kingdom Machine Learning Group UiT The Arctic University of Norway Tromsø Norway School of Intelligent Systems Engineering Sun Yat-Sen University Guangdong Guangzhou China Computational Biology Department Carnegie Mellon University PittsburghPA United States Machine Learning Department Carnegie Mellon University PittsburghPA United States Mohamed bin Zayed University of Artificial Intelligence Masdar City Abu Dhabi United Arab Emirates

The data-driven nature of deep learning (DL) models for semantic segmentation requires a large number of pixel-level annotations. However, large-scale and fully labeled medical datasets are often unavailable for practical tasks. Recently, partially supervised methods have been proposed to utilize images with incomplete labels in the medical domain. To bridge the methodological gaps in partially supervised learning (PSL) under data scarcity, we propose Vicinal Labels Under Uncertainty (VLUU), a simple yet efficient framework utilizing the human structure similarity for partially supervised medical image segmentation. Motivated by multi-task learning and vicinal risk minimization, VLUU transforms the partially supervised problem into a fully supervised problem by generating vicinal labels. We systematically evaluate VLUU under the challenges of small-scale data, dataset shift, and class imbalance on two commonly used segmentation datasets for the tasks of chest organ segmentation and optic disc-and-cup segmentation. The experimental results show that VLUU can consistently outperform previous partially supervised models in these settings. Our research suggests a new research direction in label-efficient deep learning with partial supervision. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

Meta-transfer learning through hard tasks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Sun, Qianru Liu, Yaoyao Chen, Zhaozheng Chua, Tat-Seng Schiele, Bernt School of Information Systems Singapore Management University School of Electrical and Information Engineering Tianjin University School of Computing National University of Singapore Department of Computer Vision and Machine Learning Max-Plank Institute for Informatics

Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which only a few labeled samples are available. As deep neural networks (DNNs) tend to overfit using a few samples only, typical meta-learning models use shallow neural networks, thus limiting its effectiveness. In order to achieve top performance, some recent works tried to use the DNNs pre-trained on large-scale datasets but mostly in straight-forward manners, e.g., (1) taking their weights as a warm start of meta-training, and (2) freezing their convolutional layers as the feature extractor of base-learners. In this paper, we propose a novel approach called meta-transfer learning (MTL) which learns to transfer the weights of a deep NN for few-shot learning tasks. Specifically, meta refers to training multiple tasks, and transfer is achieved by learning scaling and shifting functions of DNN weights for each task. In addition, we introduce the hard task (HT) meta-batch scheme as an effective learning curriculum that further boosts the learning efficiency of MTL. We conduct few-shot learning experiments and report top performance for five-class few-shot recognition tasks on three challenging benchmarks: miniImageNet, tieredImageNet and Fewshot-CIFAR100 (FC100). Extensive comparisons to related works validate that our MTL approach trained with the proposed HT meta-batch scheme achieves top performance. An ablation study also shows that both components contribute to fast convergence and high accuracy. Compared to the conference version of the paper [1], this version additionally presents (1) the analysis of using different DNN architectures, e.g., ResNet-12, ResNet-18 and ResNet-25;(2) the new MTL variants that adapt our scaling and shifting functions to the classical supervised and the state-of-the-art semi-supervised meta-learners, and

关键词： Deep neural networks