检索结果-内蒙古大学图书馆

PGAD: Prototype-Guided Adaptive Distillation for Multi-Modal Learning in AD Diagnosis

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Yanfei Yin, Teng Shang, Wenyi Liu, Jingyu Wang, Xi Zhao, Kaiyang Machine Intelligence Lab College of Computer Science and Technology Sichuan University Chengdu China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Department of Neurosurgery West China Hospital of Sichuan University Chengdu China

Missing modalities pose a major issue in Alzheimer’s Disease (AD) diagnosis, as many subjects lack full imaging data due to cost and clinical constraints. While multi-modal learning leverages complementary information, most existing methods train only on complete data, ignoring the large proportion of incomplete samples in real-world datasets like ADNI. This reduces the effective training set and limits the full use of valuable medical data. While some methods incorporate incomplete samples, they fail to effectively address inter-modal feature alignment and knowledge transfer challenges under high missing rates. To address this, we propose a Prototype-Guided Adaptive Distillation (PGAD) framework that directly incorporates incomplete multi-modal data into training. PGAD enhances missing modality representations through prototype matching and balances learning with a dynamic sampling strategy. We validate PGAD on the ADNI dataset with varying missing rates (20%, 50%, and 70%) and demonstrate that it significantly outperforms state-of-the-art approaches. Ablation studies confirm the effectiveness of prototype matching and adaptive sampling, highlighting the potential of our framework for robust and scalable AD diagnosis in real-world clinical settings. Copyright © 2025, The Authors. All rights reserved.

关键词： Neurodegenerative diseases

Quantus: An explainable ai toolkit for responsible evaluation of neural network explanations and beyond

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of machine Learning Research 2023年第1期24卷 1339-1349页

作者： Anna Hedström Leander Weber Dilyara Bareeva Daniel Krakowczyk Franz Motzkus Wojciech Samek Sebastian Lapuschkin Marina M.-C. Höhne Understandable Machine Intelligence Lab TU Berlin Berlin Germany Department of Artificial Intelligence Fraunhofer Heinrich-Hertz-Institute Berlin Germany Department of Computer Science University of Potsdam Potsdam Germany Department of Electrical Engineering and Computer Science TU Berlin and Department of Artificial Intelligence Fraunhofer Heinrich-Hertz-Institute Berlin Germany Understandable Machine Intelligence Lab TU Berlin Berlin Germany and BIFOLD - Berlin Institute for the Foundations of Learning and Data Berlin Germany

The evaluation of explanation methods is a research topic that has not yet been explored deeply, however, since explainability is supposed to strengthen trust in artificial intelligence, it is necessary to systematically review and compare explanation methods in order to confirm their correctness. Until now, no tool with focus on XAI evaluation exists that exhaustively and speedily allows researchers to evaluate the performance of explanations of neural network predictions. To increase transparency and reproducibility in the field, we therefore built Quantus--a comprehensive, evaluation toolkit in Python that includes a growing, well-organised collection of evaluation metrics and tutorials for evaluating explainable methods. The toolkit has been thoroughly tested and is available under an open-source license on PyPi (or on https://***/understandable-machine-intelligence-lab/Quantus/).

关键词： explainability responsible AI reproducibility open source Python

Graph Convolution Based Efficient Re-Ranking for Visual Retrieval

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Yuqi Qian, Qi Wang, Hongsong Liu, Chong Chen, Weihua Wang, Fan Machine intelligence Technology Lab Alibaba Group China Department of Computer Science and Engineering Southeast University Nanjing China

Visual retrieval tasks such as image retrieval and person re-identification (Re-ID) aim at effectively and thoroughly searching images with similar content or the same identity. After obtaining retrieved examples, re-ranking is a widely adopted post-processing step to reorder and improve the initial retrieval results by making use of the contextual information from semantically neighboring samples. Prevailing re-ranking approaches update distance metrics and mostly rely on inefficient crosscheck set comparison operations while computing expanded neighbors based distances. In this work, we present an efficient re-ranking method which refines initial retrieval results by updating features. Specifically, we reformulate re-ranking based on Graph Convolution Networks (GCN) and propose a novel Graph Convolution based Re-ranking (GCR) for visual retrieval tasks via feature propagation. To accelerate computation for large-scale retrieval, a decentralized and synchronous feature propagation algorithm which supports parallel or distributed computing is introduced. In particular, the plain GCR is extended for cross-camera retrieval and an improved feature propagation formulation is presented to leverage affinity relationships across different cameras. It is also extended for video-based retrieval, and Graph Convolution based Re-ranking for Video (GCRV) is proposed by mathematically deriving a novel profile vector generation method for the tracklet. Without bells and whistles, the proposed approaches achieve state-of-the-art performances on seven benchmark datasets from three different tasks, i.e., image retrieval, person Re-ID and video-based person Re-ID. Code is publicly available: ***/WesleyZhang1991/GCN_rerank. © 2023, CC BY.

关键词： Convolution

Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Arrabi, Ahmad Zhang, Xiaohan Sultani, Waqas Chen, Chen Wshah, Safwan Vermont Artificial Intelligence Lab. Department of Computer Science University of Vermont United States Intelligent Machines Lab. Information Technology University Center for Research in Computer Vision University of Central Florida United States

Aerial imagery analysis is critical for many research fields. However, obtaining frequent high-quality aerial images is not always accessible due to its high effort and cost requirements. One solution is to use the Ground-to-Aerial (G2A) technique to synthesize aerial images from easily collectible ground images. However, G2A is rarely studied, because of its challenges, including but not limited to, the drastic view changes, occlusion, and range of visibility. In this paper, we present a novel Geometric Preserving Ground-to-Aerial (G2A) image synthesis (GPG2A) model that can generate realistic aerial images from ground images. GPG2A consists of two stages. The first stage predicts the Bird’s Eye View (BEV) segmentation (referred to as the BEV layout map) from the ground image. The second stage synthesizes the aerial image from the predicted BEV layout map and text descriptions of the ground image. To train our model, we present a new multi-modal cross-view dataset, namely VIGORv2, built upon VIGOR [66] with newly collected aerial images, maps, and text descriptions. Our extensive experiments illustrate that GPG2A synthesizes better geometry-preserved aerial images than existing models. We also present two applications, data augmentation for cross-view geo-localization and sketch-based region search, to further verify the effectiveness of our GPG2A. The code and dataset are available at https://***/vail-uvm/gpg2a. Copyright © 2024, The Authors. All rights reserved.

关键词： Aerial photography

Scalable and Effective Arithmetic Tree Generation for Adder and Multiplier Designs

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lai, Yao Liu, Jinxin Pan, David Z. Luo, Ping Department of Computer Science The University of Hong Kong Hong Kong Machine Intelligence Lab Westlake University Zhejiang Hangzhou China Department of Electrical & Computer Engineering The University of Texas at Austin AustinTX United States

Across a wide range of hardware scenarios, the computational efficiency and physical size of the arithmetic units significantly influence the speed and footprint of the overall hardware system. Nevertheless, the effectiveness of prior arithmetic design techniques proves inadequate, as it does not sufficiently optimize speed and area, resulting in a reduced processing rate and larger module size. To boost the arithmetic performance, in this work, we focus on the two most common and fundamental arithmetic modules: adders and multipliers. We cast the design tasks as single-player tree generation games, leveraging reinforcement learning techniques to optimize their arithmetic tree structures. Such a tree generation formulation allows us to efficiently navigate the vast search space and discover superior arithmetic designs that improve computational efficiency and hardware size within just a few hours. For adders, our approach discovers designs of 128-bit adders that achieve Pareto optimality in theoretical metrics. Compared with the state-of-the-art PrefixRL, our method decreases computational delay and hardware size by up to 26% and 30%, respectively. For multipliers, when compared to RL-MUL, our approach increases speed and reduces size by as much as 49% and 45%. Moreover, the inherent flexibility and scalability of our method enable us to deploy our designs into cutting-edge technologies, as we show that they can be seamlessly integrated into 7nm technology. We believe our work will offer valuable insights into hardware design, further accelerating speed and reducing size through the refined search space and our tree generation methodologies. See our introduction video at ***/ArithmeticTree. Codes are released at ***/laiyao1/ArithmeticTree. © 2024, CC BY-NC-SA.

关键词： Computational efficiency

Two Novel Methods for Multiple Kinect v2 Sensor Calibration 6th

学校读者我要写书评

暂无评论

Two Novel Methods for Multiple Kinect v2 Sensor Calibration

6th International Conference on computer vision and Image Processing, CVIP 2021

作者： Hazra, Sumit Pisipati, Manasa Puhan, Amrit Nandy, Anup Scherer, Rafal Machine Intelligence and Bio-Motion Research Lab Department of Computer Science and Engineering NIT Rourkela Odisha Rourkela769008 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Telangana Hyderabad500075 India Department of Intelligent Computer Systems Czestochowa University of Technology al. Armii Krajowej 36 Czestochowa42-200 Poland

ISBN: (纸本)9783031113482

Camera calibration is an essential step for measuring an instrument’s accuracy by using its parameters. In this paper, we propose two methods for calibrating eight Kinect v2.0 sensors, namely, pairwise and simultaneous single-camera calibration. In the first method, an experimental setup is managed so that the eight Kinect cameras can view a 3D object on a treadmill in consecutive pairs. The novelty of this method infers pairwise calibration of eight Kinects using six steps, specifically: precalibration process, acquiring images from Kinect, exporting the parameters, generation of independent live point clouds, feeding exported parameters for point cloud matching and ensuring successful calibration through merged point clouds. In the second method, a novel octagonal model is developed to calibrate each of the eight cameras on the same experimental setup. We obtain an overall mean reprojection error of 1.37 pixels and 0.42 pixels for the first method and second method, respectively. The smallest reprojection error for the first method is reported to be 0.63 pixels and 0.27 pixels for the second method. The efficiency of the proposed methods is compared with the state-of-art techniques using the root mean square and the reprojection error metrics. We observed that the proposed methods outperform the existing techniques. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Pixels

MDNet: Multi-Decoder Network for Abdominal CT Organs Segmentation

学校读者我要写书评

暂无评论

MDNet: Multi-Decoder Network for Abdominal CT Organs Segment...

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

作者： Debesh Jha Nikhil Kumar Tomar Koushik Biswas Gorkem Durak Matthew Antalek Zheyuan Zhang Bin Wang Md Mostafijur Rahman Hongyi Pan Alpay Medetalibeyoglu Vandan Gorade Abhijit Das Yury Velichko Daniela Ladner Amir Borhani Ulas Bagci Department of Computer Science University of South Dakota Vermillion USA Department of Radiology Machine & Hybrid Intelligence Lab Northwestern University Chicago USA Department of ECE The University of Texas at Austin USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurate segmentation of organs from abdominal CT scans is essential for clinical applications such as diagnosis, treatment planning, and patient monitoring. To handle challenges of heterogeneity in organ shapes, sizes, and complex anatomical relationships, we propose a Multi decoder network (MDNet), an encoder-decoder network that uses the pre-trained MiT-B2 as the encoder and multiple different decoder networks. Each decoder network is connected to a different part of the encoder via a multi-scale feature enhancement dilated block. With each decoder, we increase the depth of the network iteratively and refine segmentation masks, enriching feature maps by integrating previous decoders’ feature maps. To refine the feature map further, we also utilize the predicted masks from the previous decoder to the current decoder to provide spatial attention across foreground and background regions. MDNet effectively refines the segmentation mask with a high dice similarity coefficient (DSC) of 0.9013 and 0.9169 on the Liver Tumor segmentation (LiTS) and MSD Spleen datasets. Additionally, it reduces Hausdorff distance (HD) to 3.79 for the LiTS dataset and 2.26 for the spleen segmentation dataset, underscoring the precision of MDNet in capturing the complex contours. Moreover, MDNet is more interpretable and robust compared to the other baseline models. The code for our architecture is available at https://***/DebeshJha/MDNet.

关键词： Spleen Heating systems Patient monitoring Shape Computed tomography Liver Decoding Planning Speech processing Tumors

Pipe-BD: Pipelined Parallel Blockwise Distillation

学校读者我要写书评

暂无评论

Pipe-BD: Pipelined Parallel Blockwise Distillation

Design, Automation and Test in Europe Conference and Exhibition

作者： Hongsun Jang Jaewon Jung Jaeyong Song Joonsang Yu Youngsok Kim Jinho Lee Department of Electrical and Computer Engineering Seoul National University Department of Artificial Intelligence Yonsei University Department of Computer Science Yonsei University CLOVA Image Vision CLOVA AI Lab NAVER

Training large deep neural network models is highly challenging due to their tremendous computational and mem-ory requirements. Blockwise distillation provides one promising method towards faster convergence by splitting a large model into multiple smaller models. In state-of-the-art blockwise distillation methods, training is performed block-by-block in a data-parallel manner using multiple GPUs. To produce inputs for the student blocks, the teacher model is executed from the beginning until the current block under training. However, this results in a high overhead of redundant teacher execution, low GPU utilization, and extra data loading. To address these problems, we propose Pipe-BD, a novel parallelization method for blockwise distillation. Pipe-BD aggressively utilizes pipeline parallelism for blockwise distillation, eliminating redundant teacher block execution and increasing per-device batch size for better resource utilization. We also extend to hybrid parallelism for efficient workload balancing. As a result, Pipe-BD achieves significant acceleration without modifying the mathematical formulation of blockwise distillation. We implement Pipe-BD on PyTorch, and experiments reveal that Pipe-BD is effective on multiple scenarios, models, and datasets.

关键词：

StaR Maps: Unveiling Uncertainty in Geospatial Relations

学校读者我要写书评

暂无评论

StaR Maps: Unveiling Uncertainty in Geospatial Relations

International Conference on Intelligent Transportation

作者： Benedict Flade Simon Kohaut Julian Eggert Devendra Singh Dhami Kristian Kersting Honda Research Institute Europe GmbH Offenbach Germany Department of Computer Science Artificial Intelligence and Machine Learning Lab TU Darmstadt Darmstadt Germany Department of Mathematics and Computer Science Uncertainty in Artificial Intelligence Group TU Eindhoven Eindhoven MB Netherlands Hessian AI Centre for Cognitive Science German Center for Artificial Intelligence (DFKI)

ISBN: (数字)9798331505929

ISBN: (纸本)9798331505936

The growing complexity of intelligent transportation systems and their applications in public spaces has increased the demand for expressive and versatile knowledge representation. While various mapping efforts have achieved widespread coverage, including detailed annotation of features with semantic labels, it is essential to understand their inherent uncertainties, which are commonly underrepresented by the respective geographic information systems. Hence, it is critical to develop a representation that combines a statistical, probabilistic perspective with the relational nature of geospatial data. Further, such a representation should facilitate an honest view of the data's accuracy and provide an environment for high-level reasoning to obtain novel insights from task-dependent queries. Our work addresses this gap in two ways. First, we present Statistical Relational Maps (StaR Maps) as a representation of uncertain, semantic map data. Second, we demonstrate efficient computation of StaR Maps to scale the approach to wide urban spaces. Through experiments on real-world, crowd-sourced data, we underpin the application and utility of StaR Maps in terms of representing uncertain knowledge and reasoning for complex geospatial information.

关键词： Vocabulary Uncertainty Navigation Semantics Urban areas Stars Probabilistic logic Cognition Geospatial analysis Computational efficiency