检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Yating Xu Chen Li Gim Hee Lee Department of Computer Science National University of Singapore Institute of High Performance Computing A*STAR and Centre for Frontier AI Research A*STAR

ISBN: (纸本)9798331314385

The key challenge of multi-view indoor 3D object detection is to infer accurate geometry information from images for precise 3D detection. Previous method relies on NeRF for geometry reasoning. However, the geometry extracted from NeRF is generally inaccurate, which leads to sub-optimal detection performance. In this paper, we propose MVSDet which utilizes plane sweep for geometry-aware 3D object detection. To circumvent the requirement for a large number of depth planes for accurate depth prediction, we design a probabilistic sampling and soft weighting mechanism to decide the placement of pixel features on the 3D volume. We select multiple locations that score top in the probability volume for each pixel and use their probability score to indicate the confidence. We further apply recent pixel-aligned Gaussian Splatting to regularize depth prediction and improve detection performance with little computation overhead. Extensive experiments on ScanNet and ARKitScenes datasets are conducted to show the superiority of our model. Our code is available at https://***/Pixie8888/MVSDet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pronounced advance on typhoon track forecast with global convection-permitting model

引用

science Bulletin 2025年第9期70卷 1424-1428页

作者： Gu, Jun Zhao, Chun Li, Gudongze Feng, Jiawang Xu, Mingyue Du, Qiuyan Xia, Zihan Li, Yubin Chen, Guanghua Hao, Xiaoyu Chen, Junshi An, Hong Deep Space Exploration Laboratory/School of Earth and Space Sciences/CMA-USTC Laboratory of Fengyun Remote Sensing/State Key Laboratory of Fire Science/Institute of Advanced Interdisciplinary Research on High-Performance Computing Systems and Software University of Science and Technology of China Hefei230026 China Laoshan Laboratory Qingdao266237 China CAS Center for Excellence in Comparative Planetology University of Science and Technology of China Hefei230026 China School of Atmospheric Physics Nanjing University of Information Science and Technology Nanjing210044 China Key Laboratory of Cloud-Precipitation Physics and Severe Storms Institute of Atmospheric Physics Chinese Academy of Sciences Beijing100029 China School of Computer Science and Technology University of Science and Technology of China Hefei230026 China

来源：评论

学校读者我要写书评

暂无评论

Learning Physics-Informed Color-Aware Transforms for Low-Light Image Enhancement

arXiv

引用

arXiv 2025年

作者： Yang, Xingxing Chen, Jie Yang, Zaifeng Department of Computer Science Hong Kong Baptist University Hong Kong Institute of High Performance Computing Agency for Science Technology and Research Singapore

Image decomposition offers deep insights into the imaging factors of visual data and significantly enhances various advanced computer vision tasks. In this work, we introduce a novel approach to low-light image enhancement based on decomposed physics-informed priors. Existing methods that directly map low-light to normal-light images in the sRGB color space suffer from inconsistent color predictions and high sensitivity to spectral power distribution (SPD) variations, resulting in unstable performance under diverse lighting conditions. To address these challenges, we introduce a Physics-informed Color-aware Transform (PiCat), a learning-based framework that converts low-light images from the sRGB color space into deep illumination-invariant descriptors via our proposed Color-aware Transform (CAT). This transformation enables robust handling of complex lighting and SPD variations. Complementing this, we propose the Content-Noise Decomposition Network (CNDN), which refines the descriptor distributions to better align with well-lit conditions by mitigating noise and other distortions, thereby effectively restoring content representations to low-light images. The CAT and the CNDN collectively act as a physical prior, guiding the transformation process from low-light to normal-light domains. Our proposed PiCat framework demonstrates superior performance compared to state-of-the-art methods across five benchmark datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

EAUWSeg: Eliminating annotation uncertainty in weakly-supervised medical image segmentation

arXiv

引用

arXiv 2025年

作者： Wang, Lituan Zhang, Lei Wang, Yan Wang, Zhenbin Zhang, Zhenwei Yi, Zhang The Machine Intelligence Laboratory College of Computer Science Sichuan University Chengdu610065 China The Institute of High Performance Computing A*STAR 138632 Singapore

Weakly-supervised medical image segmentation is gaining traction as it requires only rough annotations rather than accurate pixel-to-pixel labels, thereby reducing the workload for specialists. Although some progress has been made, there is still a considerable performance gap between the label-efficient methods and fully-supervised one, which can be attributed to the uncertainty nature of these weak labels. To address this issue, we propose a novel weak annotation method coupled with its learning framework EAUWSeg to eliminate the annotation uncertainty. Specifically, we first propose the Bounded Polygon Annotation (BPAnno) by simply labeling two polygons for a lesion. Then, the tailored learning mechanism that explicitly treat bounded polygons as two separated annotations is proposed to learn invariant feature by providing adversarial supervision signal for model training. Subsequently, a confidence-auxiliary consistency learner incorporates with a classification-guided confidence generator is designed to provide reliable supervision signal for pixels in uncertain region by leveraging the feature presentation consistency across pixels within the same category as well as class-specific information encapsulated in bounded polygons annotation. Experimental results demonstrate that EAUWSeg outperforms existing weakly-supervised segmentation methods. Furthermore, compared to fully-supervised counterparts, the proposed method not only delivers superior performance but also costs much less annotation workload. This underscores the superiority and effectiveness of our approach. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

AsT: An Asymmetric-Sensitive Transformer for Osteonecrosis of the Femoral Head Detection 37

AsT: An Asymmetric-Sensitive Transformer for Osteonecrosis o...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Chen, Haoyang Liu, Shuai Lu, Feng Li, Wei Sheng, Bin Li, Mi Jin, Hai Zomaya, Albert Y. National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Centre for Distributed and High Performance Computing School of Computer Science The University of Sydney Australia Department of Computer Science and Engineering Shanghai Jiao Tong University China Tongji Hospital Tongji Medical College Huazhong University of Science and Technology China

ISBN: (纸本)9781577358800

Early diagnosis of osteonecrosis of the femoral head (ONFH) can inhibit the progression and improve femoral head preservation. The radiograph difference between early ONFH and healthy ones is not apparent to the naked eye. It is also hard to produce a large dataset to train the classification model. In this paper, we propose Asymmetric-Sensitive Transformer (AsT) to capture the uneven development of the bilateral femoral head to enable robust ONFH detection. Our ONFH detection is realized using the self-attention mechanism to femoral head regions while conferring sensitivity to the uneven development by the attention-shared transformer. The real-world experiment studies show that AsT achieves the best performance of AUC 0.9313 in the early diagnosis of ONFH and can find out misdiagnosis cases firmly. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Research on Effectiveness of Contrastive Learning with Adversarial Examples for Different Downstream Tasks 3

Research on Effectiveness of Contrastive Learning with Adver...

引用

3rd IEEE International Conference on Frontiers Technology of Information and computer, ICFTIC 2021

作者： Zhang, Bin Sun, Yuxia Chen, Zhao Luo, Liang Xu, Yingmei Jinan University Guangdong Provincial Key Laboratory of High-Performance Computing Department of Computer Science Guangzhou China Jinan University Department of Computer Science Guangzhou China Guangdong Science Technology Infrastructure Center Guangdong Provincial Key Laboratory of High-Performance Computing Guangzhou China

ISBN: (纸本)9781665406055

Contrastive learning is a new self-supervised representation learning technique, which is considered to have great potential to improve the performance of downstream learning tasks. Recently, some researchers have conducted experiments on some datasets and found that contrastive learning based on adversarial examples can improve the performance of some image classification tasks. However, does contrastive learning with adversarial examples really benefit the performance of various downstream tasks? At present, there is still a lack of in-depth research on this issue. In this paper, we introduce a contrastive learning method with adversarial examples based on different adversarial perturbations intensities, and establish a variety of downstream image classification tasks. Experiments on different types of downstream tasks show that contrastive learning based on adversarial examples may not improve the performance of downstream tasks. We also find that the adversarial perturbation intensity and the proportion of the adversarial perturbation loss in contrastive loss are important factors affecting the above performance. © 2021 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Efficient quantum process tomography for Clifford circuits

引用

Physical Review A 2023年第3期108卷 032419-032419页

作者： Shichuan Xue Guangyao Huang Yong Liu Dongyang Wang Weixu Shi Yingwen Liu Xiang Fu Anqi Huang Mingtang Deng Junjie Wu Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha 410073 China

A Clifford circuit is a pivotal tool in quantum computing and has extensive applications in quantum error correction codes and topological quantum computing. Hence, it is essential to benchmark and verify the effect of Clifford circuits against noise and errors. Standard quantum process tomography is a fundamental technique for fully characterizing quantum dynamics, but at the cost of exponential time, space, and computation with an increasing number of qubits. Here, we propose an efficient quantum process tomography method for Clifford circuits. Combining with the stabilizer formalism, we prove theoretically that, for an n-qubit Clifford circuit, our method merely needs m ancillary qubits and ⌈n/m⌉ input stabilizer states to obtain the quantum process. Numerical simulation results show that our method could perfectly rebuild the unknown Clifford quantum circuit with fidelity over 99.99% to six qubit cases. Our work provides an efficient and practical approach to benchmark and verify Clifford circuits.

关键词： Quantum circuits Quantum information processing Quantum simulation Quantum tomography

来源：评论

学校读者我要写书评

暂无评论

Constructions of Sidon spaces and cyclic subspace codes

引用

Frontiers of Mathematics in China 2022年第2期17卷 275-288页

作者： He ZHANG Xiwang CAO Department of Mathematics Nanjing University of Aeronautics and AstronauticsNanjing 211100China School of Mathematics and Information Science Guangzhou UniversityGuangzhou 510006China Key Laboratory of Mathematical Modelling and High Performance Computing of Air Vehicles(NUAA) MIITNanjing 211106China

In this paper,we firstly construct several new kinds of Sidon spaces and Sidon sets by investigating some known ***,using these Sidon spaces,we will present a construction of cyclic subspace codes with cardinality τ,q^(n)-1/q-1 and minimum distance 2k-2,whereτis a positive *** further-more give some cyclic subspace codes with size 2τ·q^(n)-1/q-1 and without changing the minimum distance 2k-2.

关键词： Sidon spaces Sidon sets cyclic subspace codes minimum distance

来源：评论

学校读者我要写书评

暂无评论

AN INDEFINITE-PROXIMAL-BASED STRICTLY CONTRACTIVE PEACEMAN-RACHFORD SPLITTING METHOD

引用

Journal of Computational Mathematics 2023年第6期41卷 1017-1040页

作者： Yan Gu Bo Jiang Deren Han Department of Mathematics Nanjing University of Aeronautics and AstronauticsNanjing210016China Key Laboratory of Mathematical Modelling and High Performance Computing of Air Vehicles(NUAA) MIITNanjing210016China School of Mathematical Sciences Key Laboratory for NSLSCS of Jiangsu ProvinceNanjing Normal UniversityNanjing210023China LMIB School of Mathematics and Systems ScienceBeihang UniversityBeijing100191China Key Laboratory for NSLSCS of Jiangsu Province China

The Peaceman-Rachford splitting method is efficient for minimizing a convex optimization problem with a separable objective function and linear ***,its convergence was not guaranteed without extra *** et al.(SIAM ***.24:1011-1040,2014)proved the convergence of a strictly contractive Peaceman-Rachford splitting method by employing a suitable underdetermined relaxation *** this paper,we further extend the so-called strictly contractive Peaceman-Rachford splitting method by using two different relaxation ***,motivated by the recent advances on the ADMM type method with indefinite proximal terms,we employ the indefinite proximal term in the strictly contractive Peaceman-Rachford splitting *** show that the proposed indefinite-proximal strictly contractive Peaceman-Rachford splitting method is convergent and also prove the o(1/t)convergence rate in the nonergodic *** numerical tests on the l 1 regularized least square problem demonstrate the efficiency of the proposed method.

关键词： Indefinite proximal Strictly contractive Peaceman-Rachford splitting method Convex minimization Convergence rate

来源：评论

学校读者我要写书评

暂无评论

Cerasure: Fast Acceleration Strategies For XOR-Based Erasure Codes

Cerasure: Fast Acceleration Strategies For XOR-Based Erasure...

引用

IEEE International Conference on computer Design: VLSI in computers and Processors, (ICCD)

作者： Tianyang Niu Min Lyu Wei Wang Qiliang Li Yinlong Xu AnHui Province Key Laboratory of High Performance Computing School of Computer Science and Technology University of Science and Technology of China

Erasure coding is a common redundancy scheme for tolerating failures in storage systems. Compared with replication, erasure coding saves a large amount of storage space, but incurs heavy computation overhead and thus is more time-consuming. To this end, we design an algorithm to find a better parity coding matrix to reduce the number of XORs in coding based on Vandermonde matrices instead of Cauchy matrices. In addition, we optimize the coding process, to accelerate the computation speed of XOR and obtain a better tradeoff between spatial locality and computation efficiency. For wide stripes which becomes increasingly interesting, we propose to decompose the coding procedure into multiple subprocedures for better utilization of spatial locality. We integrate these methods into coding procedure and implement an erasure coding library, Cerasure. Extensive experiments show that Cerasure significantly improves the coding speed. Compared with the state-of-the-art erasure coding libraries, Zerasure and SLPEC, Cerasure increases the encoding throughput by up to 109.47%.

关键词：

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：