检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Malić, Dušan Fruhwirth-Reisinger, Christian Possegger, Horst Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Austria

LiDAR 3D object detection models are inevitably biased towards their training dataset. The detector clearly exhibits this bias when employed on a target dataset, particularly towards object sizes. However, object sizes vary heavily between domains due to, for instance, different labeling policies or geographical locations. State-of-the-art unsupervised domain adaptation approaches outsource methods to overcome the object size bias. Mainstream size adaptation approaches exploit target domain statistics, contradicting the original unsupervised assumption. Our novel unsupervised anchor calibration method addresses this limitation. Given a model trained on the source data, we estimate the optimal target anchors in a completely unsupervised manner. The main idea stems from an intuitive observation: by varying the anchor sizes for the target domain, we inevitably introduce noise or even remove valuable object cues. The latent object representation, perturbed by the anchor size, is closest to the learned source features only under the optimal target anchors. We leverage this observation for anchor size optimization. Our experimental results show that, without any retraining, we achieve competitive results even compared to state-of-the-art weakly-supervised size adaptation approaches. In addition, our anchor calibration can be combined with such existing methods, making them completely unsupervised. © 2022, CC BY.

关键词： Anchors

来源：评论

学校读者我要写书评

暂无评论

A Generalized Subspace Distribution Adaptation Framework for Cross-Corpus Speech Emotion Recognition 48

A Generalized Subspace Distribution Adaptation Framework for...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Li, Shaokai Song, Peng Ji, Liang Jin, Yun Zheng, Wenming Yantai University School of Computer and Control Engineering China Jiangsu Normal University School of Physics and Electronic Engineering China Research Center for Learning Science Southeast University Key Laboratory of Child Development and Learning Science Southeast University Ministry of Education China Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province The State Key Laboratory of Tibetan Intelligent Information Processing and Application China

ISBN: (纸本)9781728163277

In this paper, we propose a novel transfer learning framework, named generalized subspace distribution adaptation (GSDA), to tackle the challenging cross-corpus speech emotion recognition problem. First, we learn a common low-dimensional feature subspace by utilizing a generalized subspace learning method. Second, we develop a novel distance metric to reduce the divergence between the source and target corpora, which can efficiently explore the similarity and dissimilarity information in the process of knowledge transfer. Third, to demonstrate the effectiveness of our framework, we apply GSDA to the traditional subspace learning algorithms. Finally, we conduct extensive experiments by using the low-level features and deep features on three popular emotional databases, i.e., Berlin, IEMOCAP, and CVE. The results demonstrate that the proposed framework can achieve better performance than several state-of-the-art transfer learning approaches. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

vision-Language Guidance for LiDAR-based Unsupervised 3D Object Detection

arXiv

引用

arXiv 2024年

作者： Fruhwirth-Reisinger, Christian Lin, Wei Malić, Dušan Bischof, Horst Possegger, Horst Christian Doppler Laboratory for Embedded Machine Learning Austria Institute of Computer Graphics and Vision Graz University of Technology Austria Institute for Machine Learning Johannes Kepler University Linz Austria

Accurate 3D object detection in LiDAR point clouds is crucial for autonomous driving systems. To achieve state-of-the-art performance, the supervised training of detectors requires large amounts of human-annotated data, which is expensive to obtain and restricted to predefined object categories. To mitigate manual labeling efforts, recent unsupervised object detection approaches generate class-agnostic pseudo-labels for moving objects, subsequently serving as supervision signal to bootstrap a detector. Despite promising results, these approaches do not provide class labels or generalize well to static objects. Furthermore, they are mostly restricted to data containing multiple drives from the same scene or images from a precisely calibrated and synchronized camera setup. To overcome these limitations, we propose a vision-language-guided unsupervised 3D detection approach that operates exclusively on LiDAR point clouds. We transfer CLIP knowledge to classify point clusters of static and moving objects, which we discover by exploiting the inherent spatio-temporal information of LiDAR point clouds for clustering, tracking, as well as box and label refinement. Our approach outperforms state-of-the-art unsupervised 3D object detectors on the Waymo Open Dataset (+23 AP3D) and Argoverse 2 (+7.9 AP3D) and provides class labels not solely based on object size assumptions, marking a significant advancement in the field. Code will be available at https://***/chreisinger/ViLGOD. © 2024, CC BY-NC-SA.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Chinese keyword search over relational databases

Chinese keyword search over relational databases

引用

World Congress on Software Engineering

作者： Zhu, Liang Zhu, Yong Ma, Qin Key Laboratory of Machine Learning and Computational Intelligence School of Mathematics and Computer Science Hebei University Baoding Hebei 071002 China Department of Foreign Language Teaching and Research Hebei University Baoding Hebei 071002 China

ISBN: (纸本)9780769543031

Based on a knowledge base, we propose a new method to realize free-style Chinese keyword search over relational databases. Firstly, an index (also called knowledge base) is built by extracting related information of Chinese tuple words in a database, then query words and tuple words are matched quickly each other by with the index to obtain some of candidate answers for a given query. Secondly, we present a new ranking strategy to compute similarities between the query and the candidate answers, and refine the candidate answers by a matching algorithm proposed in this paper. Finally, we rank refined candidate answers to obtain top-N results. The experiments are conducted using a real dataset, and the experimental results show that our method is efficient and effective. © 2010 IEEE.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Robust feature extraction for novelty detection based on regularized correntropy criterion

Robust feature extraction for novelty detection based on reg...

引用

IEEE International Conference on Systems, Man, and Cybernetics

作者： Huan-Ru Ren Hong-Jie Xing Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University

ISBN: (纸本)9781467317139

In this paper, a robust feature extraction method based on regularized correntropy criterion (RCC) is proposed for novelty detection. In RCC, the criterion aims to maximize the difference between the correntropy of the normal data with their mean and the correntropy of the novel data with the mean of normal data. Moreover, the optimal projection vectors in the proposed objective function can be obtained by the half-quadratic (HQ) optimization technique with an iterative manner. Experimental results on one synthetic data set and nine benchmark data sets for novelty detection demonstrate that the proposed method is superior to its related approaches.

关键词： Correntropy Half-quadratic optimization Feature extraction Novelty detection Feature extraction Novelty Objective function Remote Control Center Renal Cell Carcinoma Dataset

来源：评论

学校读者我要写书评

暂无评论

Diffusion Posterior Proximal Sampling for Image Restoration 24

Diffusion Posterior Proximal Sampling for Image Restoration

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wu, Hongjie He, Linchao Zhang, Mingqin Chen, Dongdong Luo, Kunming Luo, Mengting Zhou, Ji-Zhe Chen, Hu Lv, Jiancheng College of Computer Science Sichuan University Chengdu China National Key Laboratory of Fundamental Science on Synthetic Vision Sichuan University Chengdu China Heriot-Watt University Edinburgh United Kingdom Hong Kong University of Science and Technology Hong Kong Engineering Research Center of Machine Learning and Industry Intelligence Ministry of Education China College of Computer Science Sichuan University China

ISBN: (纸本)9798400706868

Diffusion models have demonstrated remarkable efficacy in generating high-quality samples. Existing diffusion-based image restoration algorithms exploit pre-trained diffusion models to leverage data priors, yet they still preserve elements inherited from the unconditional generation paradigm. These strategies initiate the denoising process with pure white noise and incorporate random noise at each generative step, leading to over-smoothed results. In this paper, we present a refined paradigm for diffusion-based image restoration. Specifically, we opt for a sample consistent with the measurement identity at each generative step, exploiting the sampling selection as an avenue for output stability and enhancement. The number of candidate samples used for selection is adaptively determined based on the signal-to-noise ratio of the timestep. Additionally, we start the restoration process with an initialization combined with the measurement signal, providing supplementary information to better align the generative process. Extensive experimental results and analyses validate that our proposed method significantly enhances image restoration performance while consuming negligible additional computational resources. © 2024 ACM.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Determining Mice Sex from Chest X-rays using Deep learning

Determining Mice Sex from Chest X-rays using Deep Learning

引用

International Conference on Cyberspace (CYBER)

作者： Abiodun Ajiboye Kola Babalola Institute of Computer Vision and Machine Learning Lagos Nigeria European Molecular Biology Laboratory European Bioinformatics Institute Cambridgshire UK

ISBN: (纸本)9781665444095;9781665444101

This Following on from work by Babalola et al. It is shown that the sex of mice can be determined from x-ray images of the chest region alone using convolutional neural networks. The anatomical differences that may be responsible for this is further sinvestigated, as it may be useful in determining phenotype changes caused by knocking out genes - hence in understanding genotype-phenotype effects. Our results indicate that the cervical vertebrae may play an important role in the ability of our convolutional neural network to classify the sex of mice correctly using only x-rays of the chest region.

关键词： Deep learning Conferences Mice Convolutional neural networks X-ray imaging Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Interactive Deep Clustering via Value Mining 38

Interactive Deep Clustering via Value Mining

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Liu, Honglin Hu, Peng Zhang, Changqing Li, Yunfan Peng, Xi College of Computer Science Sichuan University Chengdu China College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Lab of Machine Learning Tianjin China State Key Laboratory of Hydraulics and Mountain River Engineering Sichuan University Chengdu China

In the absence of class priors, recent deep clustering methods resort to data augmentation and pseudo-labeling strategies to generate supervision signals. Though achieved remarkable success, existing works struggle to discriminate hard samples at cluster boundaries, mining which is particularly challenging due to their unreliable cluster assignments. To break such a performance bottleneck, we propose incorporating user interaction to facilitate clustering instead of exhaustively mining semantics from the data itself. To be exact, we present Interactive Deep Clustering (IDC), a plug-and-play method designed to boost the performance of pre-trained clustering models with minimal interaction overhead. More specifically, IDC first quantitatively evaluates sample values based on hardness, representativeness, and diversity, where the representativeness avoids selecting outliers and the diversity prevents the selected samples from collapsing into a small number of clusters. IDC then queries the cluster affiliations of high-value samples in a user-friendly manner. Finally, it utilizes the user feedback to finetune the pre-trained clustering model. Extensive experiments demonstrate that IDC could remarkably improve the performance of various pre-trained clustering models, at the expense of low user interaction costs. The code could be accessed at ***. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ischemic stroke identification based on EEG and EOG using ID convolutional neural network and batch normalization 8

Ischemic stroke identification based on EEG and EOG using ID...

引用

8th International Conference on Advanced computer Science and Information Systems, ICACSIS 2016

作者： Giri, Endang Purnama Fanany, Mohamad Ivan Arymurthy, Aniati Murni Wijaya, Sastra Kusuma Computer Sciences Department Faculty of Mathematics and Natural Sciences Bogor Agricultural University Bogor West Java16680 Indonesia Machine Learning and Computer Vision Laboratory Faculty of Computer Sciences Universitas Indonesia Depok West Java16424 Indonesia Department of Physics Faculty of Mathematics and Natural Sciences Universitas Indonesia Depok West Java16424 Indonesia

ISBN: (纸本)9781509046294

In 2015, stroke was the number one cause of death in Indonesia. The majority type of stroke is ischemic. The standard tool for diagnosing stroke is CT-Scan. For developing countries like Indonesia, the availability of CT-Scan is very limited and still relatively expensive. Because of the availability, another device that potential to diagnose stroke in Indonesia is EEG. Ischemic stroke occurs because of obstruction that can make the cerebral blood flow (CBF) on a person with stroke has become lower than CBF on a normal person (control) so that the EEG signal have a deceleration. On this study, we perform the ability of ID Convolutional Neural Network (1DCNN) to construct classification model that can distinguish the EEG and EOG stroke data from EEG and EOG control data. To accelerate training process our model we use Batch Normalization. Involving 62 person data object and from leave one out the scenario with five times repetition of measurement we obtain the average of accuracy 0.86 (F-Score 0.861) only at 200 epoch. This result is better than all over shallow and popular classifiers as the comparator (the best result of accuracy 0.69 and F-Score 0.72). The feature used in our study were only 24 handcrafted feature with simple feature extraction process. © 2016 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

ALFLAT: Chinese NER Using ALBERT, Flat-Lattice Transformer, Word Segmentation and Entity Dictionary 2nd

ALFLAT: Chinese NER Using ALBERT, Flat-Lattice Transformer, ...

引用

2nd EAI International Conference on Applied Cryptography in computer and Communications, AC3 2022

作者： Lv, Haifeng Ding, Yong School of Data Science and Software Engineering Wuzhou University Wuzhou China Guangxi Key Laboratory of Cryptography and Information Security School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou China

ISBN: (纸本)9783031170805

Recently, the character-word lattice structure has been proved to be effective for Chinese named entity recognition (NER) by incorporating the word information. However, one hand, since the lattice structure is dynamic and complex, although some existing lattice-based models are effectively utilize the parallel computation of GPUs, they do not fully utilize word segmentation boundary tags that as features are helpful for NER task. On the other hand, the character-word vector needs to be trained, and the user-defined entity dictionary cannot be effectively used. In this paper, we propose ALFLAT: based on a flat-lattice Transformer to incorporate ALBERT pre-trained model, word segmentation information and user-defined entity dictionary for Chinese NER. ALFLAT converts the lattice structure into a flat structure consisting of spans, integrate word segmentation embedding with the output of flat-lattice Transformer model, then modifies the emission scores according to the user-defined entity dictionary, finally utilize Viterbi decoding of the CRF layer to obtain the correct entity results. Each span corresponds to a character or latent word and its position in the original lattice. With the power of ALBERT pre-trained model, Transformer and position encoding, ALFLAT can fully leverage the lattice, word segmentation and user-defined entity dictionary information. Experiments on MSRA dataset show ALFLAT outperforms other lexicon-based models in performance and efficiency. © 2022, ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：