標(biāo)題: Titlebook: Deep Neural Networks and Data for Automated Driving; Robustness, Uncertai Tim Fingscheidt,Hanno Gottschalk,Sebastian Houben Book‘‘‘‘‘‘‘‘ 20 [打印本頁] 作者: 近地點(diǎn) 時(shí)間: 2025-3-21 17:33
書目名稱Deep Neural Networks and Data for Automated Driving影響因子(影響力)
書目名稱Deep Neural Networks and Data for Automated Driving影響因子(影響力)學(xué)科排名
書目名稱Deep Neural Networks and Data for Automated Driving網(wǎng)絡(luò)公開度
書目名稱Deep Neural Networks and Data for Automated Driving網(wǎng)絡(luò)公開度學(xué)科排名
書目名稱Deep Neural Networks and Data for Automated Driving被引頻次
書目名稱Deep Neural Networks and Data for Automated Driving被引頻次學(xué)科排名
書目名稱Deep Neural Networks and Data for Automated Driving年度引用
書目名稱Deep Neural Networks and Data for Automated Driving年度引用學(xué)科排名
書目名稱Deep Neural Networks and Data for Automated Driving讀者反饋
書目名稱Deep Neural Networks and Data for Automated Driving讀者反饋學(xué)科排名
作者: HAWK 時(shí)間: 2025-3-21 23:14
http://image.papertrans.cn/d/image/264648.jpg作者: allergy 時(shí)間: 2025-3-22 04:18 作者: aneurysm 時(shí)間: 2025-3-22 08:15 作者: Cirrhosis 時(shí)間: 2025-3-22 10:27
Deutsches Verfassungsrecht 1806 - 1918d robust deep neural network (DNN) functions requires new validation methods. A core insufficiency of DNNs is the lack of generalization for out-of-distribution datasets. One path to overcome this insufficiency is through the analysis and comparison of the domains of training and test datasets. This作者: 牽連 時(shí)間: 2025-3-22 13:54
Deutsches Verfassungsrecht 1806 - 1918its ability to simulate rare cases, avoidance of privacy issues, and generation of pixel-accurate ground truth data. Today, physical-based rendering (PBR) engines simulate already a wealth of realistic optical effects but are mainly focused on the human perception system. Whereas the perceptive func作者: 牽連 時(shí)間: 2025-3-22 18:50
Deutsches Verfassungsrecht 1806 - 1918red images, their robustness under real conditions, i.e., on images being perturbed with noise patterns or adversarial attacks, is often subject to a significantly decreased performance. In this chapter, we address this problem for the task of semantic segmentation by proposing multi-task training w作者: Accord 時(shí)間: 2025-3-23 00:46
https://doi.org/10.1007/978-3-662-64750-9 they are vulnerable to adversarial perturbations. Recent works have proven the existence of universal adversarial perturbations (UAPs), which, when added to most images, destroy the output of the respective perception function. Existing attack methods often show a low success rate when attacking ta作者: 大吃大喝 時(shí)間: 2025-3-23 02:37
Deutsches Verfassungsrecht 1806 - 1918resentations and, particularly, the invariances they capture turn neural networks into black-box models that lack interpretability. To open such a black box, it is, therefore, crucial to uncover the different semantic concepts a model has learned as well as those that it has learned to be invariant 作者: pulmonary-edema 時(shí)間: 2025-3-23 07:16
Deutsches Verfassungsrecht 1806 - 1918 medical image diagnosis. However, although the task of confidence calibration has been investigated on classification problems, thorough investigations on object detection and segmentation problems are still missing. Therefore, we focus on the investigation of confidence calibration for object dete作者: notification 時(shí)間: 2025-3-23 09:52 作者: monochromatic 時(shí)間: 2025-3-23 17:13 作者: Narcissist 時(shí)間: 2025-3-23 20:08 作者: 未完成 時(shí)間: 2025-3-23 23:36 作者: Perennial長期的 時(shí)間: 2025-3-24 05:59 作者: BILL 時(shí)間: 2025-3-24 07:25
§ 55 Wertpapiererwerbs- und übernahmegesetzcode coverage in software testing, has been proposed as one such V&V method. We provide a summary of different neuron coverage variants and their inspiration from traditional software engineering V&V methods. Our first experiment shows that novelty and granularity are important considerations when a作者: Palpitation 時(shí)間: 2025-3-24 12:31
Deutsches und internationales Steuerrechtare trained on. In this chapter, we address two insufficiencies of DNNs, namely, the lack of robustness to corruptions in the data, and the lack of real-time deployment capabilities, that need to be addressed to enable their safe and efficient deployment in real-time environments. We introduce hybri作者: ICLE 時(shí)間: 2025-3-24 17:09 作者: 使?jié)M足 時(shí)間: 2025-3-24 21:35 作者: conduct 時(shí)間: 2025-3-25 01:21
rent knowledge in neural networks and AI.Provides a basis fo.This open access book brings together the latest developments from industry and research on automated driving and artificial intelligence..Environment perception for highly automated driving heavily employs deep neural networks, facing man作者: 格言 時(shí)間: 2025-3-25 04:44 作者: 黃瓜 時(shí)間: 2025-3-25 11:18 作者: ABYSS 時(shí)間: 2025-3-25 13:38
§?17?Verbraucherdarlehensvertragr the system. In particular, we show how a combination of methods can be used to estimate the overall machine learning performance, as well as to evaluate and reduce the impact of ML-specific insufficiencies, both during design and operation.作者: Diuretic 時(shí)間: 2025-3-25 19:54
Uncertainty Quantification for Object Detection: Output- and Gradient-Based Approachesfor localization of uncertainty within the network architecture. We show that both sources of uncertainty are mutually non-redundant and can be combined beneficially. Furthermore, we show direct applications of uncertainty quantification by improving detection accuracy.作者: 吸引人的花招 時(shí)間: 2025-3-25 23:47
Evaluating Mixture-of-Experts Architectures for Network Aggregation baseline performance and also outperforms a simple aggregation via ensembling. A further advantage of an MoE is the increased interpretability—a comparison of pixel-wise predictions of the whole MoE model and the participating experts’ help to identify regions of high uncertainty in an input.作者: 載貨清單 時(shí)間: 2025-3-26 01:22 作者: abreast 時(shí)間: 2025-3-26 05:03 作者: 逃避現(xiàn)實(shí) 時(shí)間: 2025-3-26 10:24 作者: LARK 時(shí)間: 2025-3-26 12:49 作者: 顛簸下上 時(shí)間: 2025-3-26 18:36
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety health care, industrial plant control, or autonomous driving is highly challenging due to numerous model-inherent shortcomings. These shortcomings are diverse and range from a lack of generalization over insufficient interpretability and implausible predictions to directed attacks by means of malic作者: seroma 時(shí)間: 2025-3-26 22:57 作者: 神秘 時(shí)間: 2025-3-27 02:18 作者: 歡呼 時(shí)間: 2025-3-27 06:53 作者: temperate 時(shí)間: 2025-3-27 09:37 作者: 燒烤 時(shí)間: 2025-3-27 14:38
Improving Transferability of?Generated Universal Adversarial Perturbations for?Image Classification they are vulnerable to adversarial perturbations. Recent works have proven the existence of universal adversarial perturbations (UAPs), which, when added to most images, destroy the output of the respective perception function. Existing attack methods often show a low success rate when attacking ta作者: sleep-spindles 時(shí)間: 2025-3-27 19:04
Invertible Neural Networks for Understanding Semantics of Invariances of CNN Representationsresentations and, particularly, the invariances they capture turn neural networks into black-box models that lack interpretability. To open such a black box, it is, therefore, crucial to uncover the different semantic concepts a model has learned as well as those that it has learned to be invariant 作者: fiction 時(shí)間: 2025-3-28 01:22 作者: 讓你明白 時(shí)間: 2025-3-28 06:06 作者: 寬敞 時(shí)間: 2025-3-28 09:49
Detecting and?Learning the?Unknown in?Semantic Segmentationy are usually trained on a closed set of object classes appearing in a closed operational domain. However, this is in contrast to the open world assumption in automated driving that DNNs are deployed to. Therefore, DNNs necessarily face data that they have never encountered previously, also known as作者: nitroglycerin 時(shí)間: 2025-3-28 12:36
Evaluating Mixture-of-Experts Architectures for Network Aggregationct the most suitable distribution of the expert’s outputs for each input. An MoE thus not only relies on redundancy for increased robustness—we also demonstrate how this architecture can provide additional interpretability, while retaining performance similar to a standalone network. As an example, 作者: monogamy 時(shí)間: 2025-3-28 16:27
Safety Assurance of?Machine Learning for?Perception Functions to be defined and argued. At the same time, the use of machine learning (ML) functions is increasingly seen as a prerequisite to achieving the necessary levels of perception performance in the complex operating environments of these functions. This inevitably leads to the question of which supporti作者: 防止 時(shí)間: 2025-3-28 21:29
A Variational Deep Synthesis Approach for?Perception Validationctionality of these systems, specifically in the context of automated driving. The main contributions are the introduction of a generative, parametric description of three-dimensional scenarios in a validation parameter space, and layered scene generation process to reduce the computational effort. 作者: inveigh 時(shí)間: 2025-3-29 00:10
The Good and?the?Bad: Using Neuron Coverage as?a?DNN Validation Techniquecode coverage in software testing, has been proposed as one such V&V method. We provide a summary of different neuron coverage variants and their inspiration from traditional software engineering V&V methods. Our first experiment shows that novelty and granularity are important considerations when a作者: 易改變 時(shí)間: 2025-3-29 06:11 作者: 大酒杯 時(shí)間: 2025-3-29 08:59
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetyencies to then describe research activities aiming at their detection, quantification, or mitigation. Our work addresses machine learning experts and safety engineers alike: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent 作者: 厚臉皮 時(shí)間: 2025-3-29 13:28
Does Redundancy in AI Perception Systems Help to Test for Super-Human Automated Driving Performance?f training data, architecture, and training are kept separate or independence is trained using special loss functions. Using data from different sensors (realized by up to five 2D projections of the 3D MNIST dataset) in our experiments is more efficiently reducing correlations, however not to an ext作者: SYN 時(shí)間: 2025-3-29 16:16 作者: Cpr951 時(shí)間: 2025-3-29 21:32 作者: Discrete 時(shí)間: 2025-3-30 00:43 作者: heart-murmur 時(shí)間: 2025-3-30 06:03 作者: 情感 時(shí)間: 2025-3-30 12:09
Invertible Neural Networks for Understanding Semantics of Invariances of CNN Representationsns to (i) expose their semantic meaning, (ii) semantically modify a representation, and (iii) visualize individual learned semantic concepts and invariances. Our invertible approach significantly extends the abilities to understand black-box models by enabling post hoc interpretations of state-of-th作者: Femish 時(shí)間: 2025-3-30 12:34
Confidence Calibration for Object Detection and Segmentationion of object detection and segmentation models. We examine several network architectures on MS COCO as well as on Cityscapes and show that especially object detection as well as instance segmentation models are intrinsically miscalibrated given the introduced definition of calibration. Using our pr作者: 克制 時(shí)間: 2025-3-30 18:26 作者: 決定性 時(shí)間: 2025-3-30 22:39
A Variational Deep Synthesis Approach for?Perception Validationnd combined with our variational approach we can effectively simulate and test a wide range of additional conditions as, e.g., various illuminations. We can demonstrate that our generative approach produces a better approximation of the spatial object distribution to real datasets, compared to hand-作者: 挫敗 時(shí)間: 2025-3-31 04:27
Joint Optimization for DNN Model Compression and Corruption Robustnesstness of the . network by 8.39% absolute mean performance under corruption (mPC) on the Cityscapes dataset, and by 2.93% absolute mPC on the Sim KI-A dataset, while generalizing even to augmentations not seen by the network in the training process. This is achieved with only minor degradations on un作者: 蚊子 時(shí)間: 2025-3-31 07:01
https://doi.org/10.1007/978-3-662-39531-8encies to then describe research activities aiming at their detection, quantification, or mitigation. Our work addresses machine learning experts and safety engineers alike: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent 作者: Radiculopathy 時(shí)間: 2025-3-31 11:31 作者: 公社 時(shí)間: 2025-3-31 16:35 作者: Ibd810 時(shí)間: 2025-3-31 18:06
