检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Jo, Gyeongdeok Kim, Jonghun Park, Bo-Yong Park, Hyunjin Sungkyunkwan University Department of Electrical and Computer Engineering Suwon Korea Republic of Institute for Basic Science Center for Neuroscience Imaging Research Suwon Korea Republic of Korea University Department of Brain and Cognitive Engineering Seoul Korea Republic of

ISBN: (纸本)9798350386226

White matter hyperintensities (WMHs) are critical indicators of cerebral small vessel disease and are linked to stroke and cognitive decline. Accurate WHM segmentation is challenging due to limited contrast and small size, particularly for deep WMHs where T1-weighted and FLAIR MRI are routinely used. Image fusion offers a method to combine two modalities into one fused modality useful for WHM segmentation. We propose DeAFusion: Detail-Aware Image Fusion, a novel image fusion framework. This framework introduces a Pixel-wise Information Preservation Degree map to enable detailed control of fusion at the pixel level and incorporates segmentation loss to embed semantic information. Our model outperforms existing fusion methods in enhancing lesion visibility and preserving structural details, as demonstrated on both public and in-house datasets. DeAFusion shows promise for improving clinical assessments of WMHs. Our code is available at https://***/Gyeongdeok-Jo/DeAFusion. © 2024 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Development of Character Recognition Model Inspired by Visual Explanations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1362-1372页

作者： Ralekar, Chetan Choudhary, Shubham Gandhi, Tapan Kumar Chaudhury, Santanu Department of Brain and Cognitive Sciences Massachusetts Institute of Technology CambridgeMA02139 United States Harvard John A. Paulson School of Engineering and Applied Sciences CambridgeMA02138 United States Department of Electrical Engineering Indian Institute of Technology New Delhi110016 India Department of Computer Science and Engineering Indian Institute of Technology Jodhpur342030 India

Deep neural networks (DNNs) currently constitute the best-performing artificial vision systems. However, humans are still better at recognizing many characters, especially distorted, ornamental, or calligraphic characters compared with the highly sophisticated recognitionmodels. Understanding themechanism of character recognition by humans may give some cues for building better recognition models. However, the appropriate methodological approach to using these cues has not been much explored for developing character recognition models. Therefore, this paper tries to understand the process of character recognition by humans and DNNs by generating visual explanations for their respective decisions. We have used eye tracking to assay the spatial distribution of information hotspots for humans via fixation maps. We have proposed a gradient-based method for visualizing the reasoning behind the model's decision through visualization maps and have proved that our method is better than the other class activation mapping methods. Qualitative comparison between visualization maps and fixation maps reveals that both model and humans focus on similar regions in character in the case of correctly classified characters. However, when the focused regions are different for humans and model, the characters are typically misclassified by the latter. Hence, we propose to use the fixation maps as a supervisory input to train the model that ultimately results in improved recognition performance and better generalization. As the proposedmodel gives some insights about the reasoning behind its decision, it can find applications in fields, such as surveillance and medical applications, where explainability helps to determine system fidelity. Impact Statement-Humans and DNNs rely on selective information uptake while classifying a character. This information selection strategy can be understood by visualizing the important, informative character regions that ultimately govern the decision o

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

ConvBLS: An Effective and Efficient Incremental Convolutional Broad Learning System Combining Deep and Broad Representations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5075-5089页

作者： Lei, Chunyu Guo, Jifeng Chen, C. L. Philip South China University of Technology Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information School of Computer Science and Engineering Guangzhou510006 China Pazhou Lab Brain and Affective Cognitive Research Center Guangzhou510335 China Engineering Research Center of the Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human Guangzhou510006 China

Broad learning system (BLS) has to undergo a vectorization operation before modeling image data, which makes it challenging for BLS to learn local semantic features. Thus, various convolutional-based broad learning systems (C-BLSs) have been introduced to address these challenges. Regrettably, the existing C-BLS variants either lack an efficient training algorithm and incremental learning capability or suffer from poor performance. To this end, we propose a novel convolutional broad learning system (ConvBLS) based on the spherical K-means (SKM) algorithm and two-stage multiscale (TSMS) feature fusion, which consists of the convolutional feature layer (CFL), convolutional enhancement layer (CEL), TSMS feature fusion layer, and output layer. First, unlike the current C-BLS, the simple yet efficient SKM algorithm is utilized to learn the weights of CFLs. Compared with random filters, the SKM algorithm enables the CFL to learn more comprehensive spatial features. Second, to further mine the local semantic features, CELs are established to expand the feature space. Third, the TSMS feature fusion layer is proposed to extract more effective multiscale features by integrating deep and broad representations. Thanks to the above elaborate design and the pseudoinverse calculation of the output layer weights, our proposed ConvBLS method is unprecedentedly efficient and effective. Finally, the corresponding incremental learning algorithms are presented for rapid remodeling if the model deems to expand. Experiments and comparisons demonstrate the superiority of our method. © 2024 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Flexible mapping of abstract domains by grid cells via self-supervised extraction and projection of generalized velocity signals 38

Flexible mapping of abstract domains by grid cells via self-...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Iyer, Abhiram Chandra, Sarthak Sharma, Sugandha Fiete, Ila Department of Electrical Engineering and Computer Science MIT CambridgeMA United States Department of Brain and Cognitive Sciences MIT CambridgeMA United States McGovern Institute for Brain Research MIT CambridgeMA United States MIT CambridgeMA United States

Grid cells in the medial entorhinal cortex create remarkable periodic maps of explored space during navigation. Recent studies show that they form similar maps of abstract cognitive spaces. Examples of such abstract environments include auditory tone sequences in which the pitch is continuously varied or images in which abstract features are continuously deformed (e.g., a cartoon bird whose legs stretch and shrink). Here, we hypothesize that the brain generalizes how it maps spatial domains to mapping abstract spaces. To sidestep the computational cost of learning representations for each high-dimensional sensory input, the brain extracts self-consistent, low-dimensional descriptions of displacements across abstract spaces, leveraging the spatial velocity integration of grid cells to efficiently build maps of different domains. Our neural network model for abstract velocity extraction factorizes the content of these abstract domains from displacements within the domains to generate content-independent and self-consistent, low-dimensional velocity estimates. Crucially, it uses a self-supervised geometric consistency constraint that requires displacements along closed loop trajectories to sum to zero, an integration that is itself performed by the downstream grid cell circuit over learning. This process results in high fidelity estimates of velocities and allowed transitions in abstract domains, a crucial prerequisite for efficient map generation in these high-dimensional environments. We also show how our method outperforms traditional dimensionality reduction and deep-learning based motion extraction networks on the same set of tasks. This is the first neural network model to explain how grid cells can flexibly represent different abstract spaces and makes the novel prediction that they should do so while maintaining their population correlation and manifold structure across domains. Fundamentally, our model sheds light on the mechanistic origins of cognitive flexib

关键词：

来源：评论

学校读者我要写书评

暂无评论

Flexible Context-Driven Sensory Processing in Dynamical Vision Models 38

Flexible Context-Driven Sensory Processing in Dynamical Visi...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Govindarajan, Lakshmi Narasimhan Iyer, Abhiram Kothare, Valmiki Fiete, Ila Department of Brain and Cognitive Sciences MIT CambridgeMA United States Department of Electrical Engineering and Computer Science MIT CambridgeMA United States McGovern Institute for Brain Research MIT CambridgeMA United States MIT CambridgeMA United States

Visual representations become progressively more abstract along the cortical hierarchy. These abstract representations define notions like objects and shapes, but at the cost of spatial specificity. By contrast, low-level regions represent spatially local but simple input features. How do spatially non-specific representations of abstract concepts in high-level areas flexibly modulate the low-level sensory representations in appropriate ways to guide context-driven and goal-directed behaviors across a range of tasks? We build a biologically motivated and trainable neural network model of dynamics in the visual pathway, incorporating local, lateral, and feedforward synaptic connections, excitatory and inhibitory neurons, and long-range top-down inputs conceptualized as low-rank modulations of the input-driven sensory responses by high-level areas. We study this Dynamical Cortical network (DCnet) in a visual cue-delay-search task and show that the model uses its own cue representations to adaptively modulate its perceptual responses to solve the task, outperforming state-of-the-art DNN vision and LLM models. The model's population states over time shed light on the nature of contextual modulatory dynamics, generating predictions for experiments. We fine-tune the same model on classic psychophysics attention tasks, and find that the model closely replicates known reaction time results. This work represents a promising new foundation for understanding and making predictions about perturbations to visual processing in the brain. © 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

Development of a Digital brain Phantom Population for Radionuclide Imaging Research in Parkinson's Disease

Development of a Digital Brain Phantom Population for Radion...

引用

2022 IEEE Nuclear science Symposium, Medical Imaging Conference, and Room Temperature Semiconductor Detector Conference, IEEE NSS MIC RTSD 2022

作者： Huang, Wenbo Mok, Greta S. P. University of Macau Faculty of Science and Technology The Center for Cognitive and Brain Sciences Institute of Collaborative Innovation Department of Electrical and Computer Engineering Taipa China

ISBN: (纸本)9781665488723

Parkinson's disease (PD) can be early diagnosed using radionuclide imaging. Digital phantoms and Monte Carlo (MC) simulations serve as important research tools for PD imaging physics research. Here we designed and developed a new digital brain phantom population for different stages of PD. We selected 206 T1 MRI brain images and 160 DaTscan SPECT reconstructed images for normal subjects and patients with different PD stages from Parkinson's Progression Markers Initiative (PPMI) datasets. We used the model-based segmentation tool FIRST to segment putamen and caudate region and used brain Extraction Tool (BET) to extract brain region from the MRI images, generating striatum and brain maps, respectively. Striatum maps were then rigidly registered to a referenced striatum model using Elastix, and the corresponding brain maps were transformed using the same parameters. Different activities were set on the maps based on the striatal binding ratio (SBR) in PPMI and the SPECT Visual interpretation assessment scheme. New phantoms were generated by randomly pairing the striatum and brain maps. Corresponding CT maps were generated by non-rigidly registered the XCAT-attenuation map to MRI images corresponding to the brain maps and transformed using the same parameters. We then used the Simind MC code to generate 120 realistic noisy projections with full physics modelling for each new brain phantom, based on a clinical SPECT scanner mounted with low-energy high-resolution parallel-hole collimators. OS-EM algorithm (8 iterations, 4 subsets) was used to reconstruct projections with and without attenuation correction (AC) respectively. SBR was evaluated on reconstructed images. Our results show that we could generate realistic PD SPECT data with the newly developed digital brain phantom population combined with a MC code, and AC is important for PD SPECT based on both visual assessment and SBR analysis. Our phantoms could be applied for further PD radionuclide imaging study. © 2022

关键词：

来源：评论

学校读者我要写书评

暂无评论

Elevating Robust ASR By Decoupling Multi-Channel Speaker Separation and Speech Recognition

Elevating Robust ASR By Decoupling Multi-Channel Speaker Sep...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yufeng Yang Hassan Taherian Vahid Ahmadi Kalkhorani DeLiang Wang Department of Computer Science and Engineering The Ohio State University USA Center for Cognitive and Brain Sciences The Ohio State University USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Despite the tremendous success of automatic speech recognition (ASR) with the introduction of deep learning, its performance is still unsatisfactory in many real-world multi-talker scenarios. Speaker separation excels in separating individual talkers but, as a frontend, it introduces processing artifacts that degrade the ASR backend trained on clean speech. As a result, mainstream robust ASR systems train on noisy speech to avoid processing artifacts. In this work, we propose to decouple the training of the multi-channel speaker separation frontend and the ASR backend, with the latter trained only on clean speech. On SMS-WSJ, the proposed approach achieves a word error rate (WER) of 5.74%, outperforming the previous best by 14.3%. Furthermore, on recorded LibriCSS, we achieve the speaker-attributed WER of 3.86%, outperforming the previous best system trained on the same data by 24.8%. These state-of-the-art results suggest that decoupling speech separation and recognition is a potentially effective approach to robust ASR.

关键词： Training Deep learning Error analysis Signal processing Acoustics Noise measurement Speech processing Automatic speech recognition

来源：评论

学校读者我要写书评

暂无评论

Polysemy through the lens of psycholinguistic variables: a dataset and an evaluation of static and contextualized language models 13

Polysemy through the lens of psycholinguistic variables: a d...

引用

13th Joint Conference on Lexical and Computational Semantics, StarSEM 2024

作者： Bruera, Andrea Zamani, Farbod Poesio, Massimo Cognition and Plasticity Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany Department of Computing Goldsmiths University of London United Kingdom CogSci Research Group School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom

ISBN: (纸本)9798891761063

Polysemes are words that can have different senses depending on the context of utterance: for instance, ‘newspaper’ can refer to an organization (as in ‘manage the newspaper’) or to an object (as in ‘open the newspaper’). Contrary to a large body of evidence coming from psycholinguistics, polysemy has been traditionally modelled in NLP by assuming that each sense should be given a separate representation in a lexicon (e.g. WordNet). This led to the current situation, where datasets used to evaluate the ability of computational models of semantics miss crucial details about the representation of polysemes, thus limiting the amount of evidence that can be gained from their use. In this paper we propose a framework to approach polysemy as a continuous variation in psycholinguistic properties of a word in context. This approach accommodates different sense interpretations, without postulating clear-cut jumps between senses. First we describe a publicly available English dataset that we collected, where polysemes in context (verb-noun phrases) are annotated for their concreteness and body sensory strength. Then, we evaluate static and contextualized language models in their ability to predict the ratings of each polyseme in context, as well as in their ability to capture the distinction among senses, revealing and characterizing in an interpretable way the models’ flaws. © 2024 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Correction: Cross-linguistically consistent semantic and syntactic annotation of child-directed speech

引用

Language Resources and Evaluation 2024年第2期59卷 777-778页

作者： Szubert, Ida Abend, Omri Schneider, Nathan Gibbon, Samuel Mahon, Louis Goldwater, Sharon Steedman, Mark School of Informatics University of Edinburgh Edinburgh UK School of Computer Science and Engineering and the Department of Cognitive Science Hebrew University of Jerusalem Jerusalem Israel Departments of Linguistics and Computer Science Georgetown University Washington USA Centre for Clinical Brain Sciences University of Edinburgh Edinburgh UK

来源：评论

学校读者我要写书评

暂无评论

Combined Generative and Predictive Modeling for Speech Super-resolution

arXiv

引用

arXiv 2024年

作者： Wang, Heming Healy, Eric W. Wang, DeLiang The Department of Computer Science and Engineering The Ohio State University OH43210 United States The Department of Speech and Hearing Science The Center for Cognitive and Brain Sciences The Ohio State University ColumbusOH43210 United States The Department of Computer Science and Engineering The Center for Cognitive and Brain Sciences The Ohio State University ColumbusOH43210 United States

Speech super-resolution (SR) is the task that restores high-resolution speech from low-resolution input. Existing models employ simulated data and constrained experimental settings, which limit generalization to real-world SR. Predictive models are known to perform well in fixed experimental settings, but can introduce artifacts in adverse conditions. On the other hand, generative models learn the distribution of target data and have a better capacity to perform well on unseen conditions. In this study, we propose a novel two-stage approach that combines the strengths of predictive and generative models. Specifically, we employ a diffusion-based model that is conditioned on the output of a predictive model. Our experiments demonstrate that the model significantly outperforms single-stage counterparts and existing strong baselines on benchmark SR datasets. Furthermore, we introduce a repainting technique during the inference of the diffusion process, enabling the proposed model to regenerate high-frequency components even in mismatched conditions. An additional contribution is the collection of and evaluation on real SR recordings, using the same microphone at different native sampling rates. We make this dataset freely accessible, to accelerate progress towards real-world speech super-resolution. Copyright © 2024, The Authors. All rights reserved.

关键词： Optical resolving power

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：