检索结果-内蒙古大学图书馆

MCANet: Medical Image Segmentation with Multi-scale Cross-axis Attention

Machine Intelligence Research 2025年第3期22卷 437-451页

作者： Shao, Hao Zeng, Quansheng Hou, Qibin Yang, Jufeng Tianjin Key Laboratory of Visual Computing and Intelligent Perception College of Computer Science Nankai University Tianjin300000 China

Efficiently capturing multi-scale local information and building long-range dependencies among pixels are essential for medical image segmentation because of the various sizes and shapes of the lesion regions or organs. In this paper, we propose the multi-scale cross-axis attention (MCA) mechanism to address these challenges through enhanced axial attention. To address the issues of insufficient learning of positional bias and limited long-distance interaction in axial attention caused by the small dataset, we propose using a dual cross-attention mechanism instead of axial attention to enhance global information capture. Meanwhile, to compensate for the lack of explicit attention to local information in axial attention, we use multiple convolutions of strip-shaped kernels with different kernel sizes in each axial attention path, which improves the efficiency of MCA in local information encoding. By integrating MCA into the multi-scale cross-axis attention network (MSCAN) backbone, we develop our network architecture, termed MCANet. With merely 4 M+ parameters, MCANet outperforms previous heavyweight approaches (e.g., swin transformer-based methods) across four challenging tasks: skin lesion segmentation, nuclei segmentation, abdominal multi-organ segmentation, and polyp segmentation. The code is available at https://***/haoshao-nku/medical_seg. © Institute of Automation, Chinese Academy of Sciences and Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware Superpoint Graph Transformer for Weakly Supervised 3D Semantic Segmentation

引用

IEEE Transactions on Fuzzy Systems 2025年第6期33卷 1899-1912页

作者： Fan, Yan Wang, Yu Zhu, Pengfei Hui, Le Xie, Jin Hu, Qinghua Tianjin University College of Intelligence and Computing Tianjin300350 China Ministry of Education of the People's Republic of China Engineering Research Center of City Intelligence and Digital Governance China Haihe Laboratory of Itai Tianjin China Northwestern Polytechnical University School of Electronics and Information Shaanxi Key Laboratory of Information Acquisition and Processing China Nanjing University of Science and Technology Pca Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

Weakly supervised 3D semantic segmentation has successfully mitigated the labor-intensive and time-consuming task of annotating 3D point clouds. However, reliably utilizing the minimal point-wise annotations for unlabeled data in complex and large-scale scenes is still challenging, such as only 20 points labeled in 2 million points. To tackle this challenge, we propose a new Uncertainty-aware Superpoint Graph Transformer (UaSGT) framework that utilizes minimal annotations for unlabeled data learning through reliable long-range supervision propagation from labeled superpoints to unlabeled superpoints. First, we propose a superpoint graph transformer to achieve long-range supervision propagation along the attention-based fuzzy subsets defined on superpoints. The attention-based fuzzy subset measures the membership of unlabeled superpoints to clusters centered on labeled superpoints. Second, we employ an uncertainty-aware membership rectification technique on the fuzzy subset to ensure reliable propagation among superpoints within the same category. This technique integrates an uncertainty prediction module to mask the influence of unreliable membership and a spatial prior refinement module to reduce uncertainty in intra-class membership degrees. Finally, experimental results on two large-scale benchmarks S3DIS and ScanNet-V2 demonstrate the superiority of our approach compared to the state-of-the-art with at least 90% annotation reduction, and our method also achieves comparable performance to fully supervised methods with less than 0.1% labeled points. Our code is available at https://***/fanyan0411/UaSGT. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design 41

A Circuit Domain Generalization Framework for Efficient Logi...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Zhihai Chen, Lei Wang, Jie Bai, Yinqi Li, Xing Li, Xijun Yuan, Mingxuan Hao, Jianye Zhang, Yongdong Wu, Feng CAS Key Laboratory of Technology in GIPAS & MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China China Noah's Ark Lab Huawei Technologies China College of Intelligence and Computing Tianjin University China

Logic Synthesis (LS) plays a vital role in chip design. A key task in LS is to simplify circuits-modeled by directed acyclic graphs (DAGs)-with functionality-equivalent transformations. To tackle this task, many LS heuristics apply transformations to subgraphs-rooted at each node on an input DAG-sequentially. However, we found that a large number of transformations are ineffective, which makes applying these heuristics highly time-consuming. In particular, we notice that the runtime of the Resub and Mfs2 heuristics often dominates the overall runtime of LS optimization processes. To address this challenge, we propose a novel data-driven LS heuristic paradigm, namely PruneX, to reduce ineffective transformations. The major challenge of developing PruneX is to learn models that well generalize to unseen circuits, i.e., the out-of-distribution (OOD) generalization problem. Thus, the major technical contribution of PruneX is the novel circuit domain generalization framework, which learns domain-invariant representations based on the transformation-invariant domain-knowledge. To the best of our knowledge, PruneX is the first approach to tackle the OOD problem in LS heuristics. We integrate PruneX with the aforementioned Resub and Mfs2 heuristics. Experiments demonstrate that PruneX significantly improves their efficiency while keeping comparable optimization performance on industrial and very large-scale circuits, achieving up to 3.1× faster runtime. Copyright 2024 by the author(s)

关键词： Logic Synthesis

来源：评论

学校读者我要写书评

暂无评论

Robust and Faster Zeroth-Order Minimax Optimization: Complexity and Applications 38

Robust and Faster Zeroth-Order Minimax Optimization: Complex...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： An, Weixin Liu, Yuanyuan Shang, Fanhua Liu, Hongying Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University China College of Intelligence and Computing Tianjin University China Medical School Tianjin University China Peng Cheng Lab Shenzhen China

Many zeroth-order (ZO) optimization algorithms have been developed to solve nonconvex minimax problems in machine learning and computer vision areas. However, existing ZO minimax algorithms have high complexity and rely on some strict restrictive conditions for ZO estimations. To address these issues, we design a new unified ZO gradient descent extragradient ascent (ZO-GDEGA) algorithm, which reduces the overall complexity to O(dϵ-6) to find an ϵ-stationary point of the function ψ for nonconvex-concave (NC-C) problems, where d is the variable dimension. To the best of our knowledge, ZO-GDEGA is the first ZO algorithm with complexity guarantees to solve stochastic NC-C problems. Moreover, ZO-GDEGA requires weaker conditions on the ZO estimations and achieves more robust theoretical results. As a by-product, ZO-GDEGA has advantages on the condition number for the NC-strongly concave case. Experimentally, ZO-GDEGA can generate more effective poisoning attack data with an average accuracy reduction of 5%. The improved AUC performance also verifies the robustness of gradient estimations. © 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

Towards Next-Generation Logic Synthesis: A Scalable Neural Circuit Generation Framework 38

Towards Next-Generation Logic Synthesis: A Scalable Neural C...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Zhihai Wang, Jie Yang, Qingyue Bai, Yinqi Li, Xing Chen, Lei Hao, Jianye Yuan, Mingxuan Li, Bin Zhang, Yongdong Wu, Feng MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China China Noah's Ark Lab Huawei Technologies Canada College of Intelligence and Computing Tianjin University China

Logic Synthesis (LS) aims to generate an optimized logic circuit satisfying a given functionality, which generally consists of circuit translation and optimization. It is a challenging and fundamental combinatorial optimization problem in integrated circuit design. Traditional LS approaches rely on manually designed heuristics to tackle the LS task, while machine learning recently offers a promising approach towards next-generation logic synthesis by neural circuit generation and optimization. In this paper, we first revisit the application of differentiable neural architecture search (DNAS) methods to circuit generation and found from extensive experiments that existing DNAS methods struggle to exactly generate circuits, scale poorly to large circuits, and exhibit high sensitivity to hyper-parameters. Then we provide three major insights for these challenges from extensive empirical analysis: 1) DNAS tends to overfit to too many skip-connections, consequently wasting a significant portion of the network's expressive capabilities;2) DNAS suffers from the structure bias between the network architecture and the circuit inherent structure, leading to inefficient search;3) the learning difficulty of different input-output examples varies significantly, leading to severely imbalanced learning. To address these challenges in a systematic way, we propose a novel regularized triangle-shaped circuit network generation framework, which leverages our key insights for completely accurate and scalable circuit generation. Furthermore, we propose an evolutionary algorithm assisted by reinforcement learning agent restarting technique for efficient and effective neural circuit optimization. Extensive experiments on four different circuit benchmarks demonstrate that our method can precisely generate circuits with up to 1200 nodes. Moreover, our synthesized circuits significantly outperform the state-of-the-art results from several competitive winners in IWLS 2022 and 2023 competition

关键词：

来源：评论

学校读者我要写书评

暂无评论

Curricular Object Manipulation in LiDAR-based Object Detection

Curricular Object Manipulation in LiDAR-based Object Detecti...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Ziyue Zhu Qiang Meng Xiao Wang Ke Wang Liujiang Yan Jian Yang Tianjin Key Laboratory of Visual Computing and Intelligent Perception College of Computer Science Nankai University Didi Chuxing

This paper explores the potential of curriculum learning in LiDAR-based 3D object detection by proposing a curricular object manipulation (COM) framework. The framework embeds the curricular training strategy into both the loss design and the augmentation process. For the loss design, we propose the COMLoss to dynamically predict object-level difficulties and emphasize objects of different difficulties based on training stages. On top of the widely-used augmentation technique called GT-Aug in Li-DAR detection tasks, we propose a novel COMAug strategy which first clusters objects in ground-truth database based on well-designed heuristics. Group-level difficulties rather than individual ones are then predicted and updated during training for stable results. Model performance and generalization capabilities can be improved by sampling and augmenting progressively more difficult objects into the training samples. Extensive experiments and ablation studies reveal the superior and generality of the proposed framework. The code is available at https://***/ZZY816/COM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards General Algorithm Discovery for Combinatorial Optimization: Learning Symbolic Branching Policy from Bipartite Graph 41

Towards General Algorithm Discovery for Combinatorial Optimi...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Kuang, Yufei Wang, Jie Zhou, Yuyan Li, Xijun Zhu, Fangzhou Hao, Jianye Wu, Feng CAS Key Laboratory of Technology in GIPAS University of Science and Technology of China China MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China China Noah's Ark Lab Huawei Technologies China College of Intelligence and Computing Tianjin University China

Machine learning (ML) approaches have been successfully applied to accelerating exact combinatorial optimization (CO) solvers. However, many of them fail to explain what patterns they have learned that accelerate the CO algorithms due to the black-box nature of ML models like neural networks, and thus they prevent researchers from further understanding the tasks they are interested in. To tackle this problem, we propose the first graph-based algorithm discovery framework-namely, graph symbolic discovery for exact combinatorial optimization solver (GS4CO)-that learns interpretable branching policies directly from the general bipartite graph representation of CO problems. Specifically, we mainly focus on the variable selection part of the branching policy. We design a unified representation for symbolic variable selection policies with graph inputs, and then we employ a Transformer with multiple tree-structural encodings to generate symbolic trees end-to-end, which effectively reduces the cumulative error from iteratively distilling graph neural networks. Experiments show that GS4CO learned interpretable and lightweight policies outperform all the baselines on CPU machines, including both the human-designed and the learning-based. GS4CO shows an encouraging step towards general algorithm discovery on modern CO solvers. Codes are available at https://***/MIRALab-USTC/L2O-GS4CO. Copyright 2024 by the author(s)

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Curricular Object Manipulation in LiDAR-based Object Detection

arXiv

引用

arXiv 2023年

作者： Zhu, Ziyue Meng, Qiang Wang, Xiao Wang, Ke Yan, Liujiang Yang, Jian Tianjin Key Laboratory of Visual Computing and Intelligent Perception College of Computer Science Nankai University China Didi Chuxing China

This paper explores the potential of curriculum learning in LiDAR-based 3D object detection by proposing a curricular object manipulation (COM) framework. The framework embeds the curricular training strategy into both the loss design and the augmentation process. For the loss design, we propose the COMLoss to dynamically predict object-level difficulties and emphasize objects of different difficulties based on training stages. On top of the widely-used augmentation technique called GT-Aug in LiDAR detection tasks, we propose a novel COMAug strategy which first clusters objects in ground-truth database based on well-designed heuristics. Group-level difficulties rather than individual ones are then predicted and updated during training for stable results. Model performance and generalization capabilities can be improved by sampling and augmenting progressively more difficult objects into the training samples. Extensive experiments and ablation studies reveal the superior and generality of the proposed framework. The code is available at https://***/ZZY816/COM. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical Adaptive Multi-Task Reinforcement Learning Framework for Multiplier Circuit Design 41

A Hierarchical Adaptive Multi-Task Reinforcement Learning Fr...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Zhihai Wang, Jie Zuo, Dongsheng Ji, Yunjie Xia, Xilin Ma, Yuzhe Hao, Jianye Yuan, Mingxuan Zhang, Yongdong Wu, Feng CAS Key Laboratory of Technology in GIPAS MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China China Microelectronics Thrust Hong Kong University of Science and Technology Guangzhou China Noah's Ark Lab Huawei Technologies China College of Intelligence and Computing Tianjin University China

Multiplier design-which aims to explore a large combinatorial design space to simultaneously optimize multiple conflicting objectives-is a fundamental problem in the integrated circuits industry. Although traditional approaches tackle the multi-objective multiplier optimization problem by manually designed heuristics, reinforcement learning (RL) offers a promising approach to discover high-speed and area-efficient multipliers. However, the existing RL-based methods struggle to find Pareto-optimal circuit designs for all possible preferences, i.e., weights over objectives, in a sample-efficient manner. To address this challenge, we propose a novel hierarchical adaptive (HAVE) multi-task reinforcement learning framework. The hierarchical framework consists of a meta-agent to generate diverse multiplier preferences, and an adaptive multi-task agent to collaboratively optimize multipliers conditioned on the dynamic preferences given by the meta-agent. To the best of our knowledge, HAVE is the first to well approximate Pareto-optimal circuit designs for the entire preference space with high sample efficiency. Experiments on multipliers across a wide range of input widths demonstrate that HAVE significantly Pareto-dominates state-of-the-art approaches, achieving up to 28% larger hypervolume. Moreover, experiments demonstrate that multipliers designed by HAVE can well generalize to large-scale computation-intensive circuits. Copyright 2024 by the author(s)

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Single-Loop Accelerated Extra-Gradient Difference Algorithm with Improved Complexity Bounds for Constrained Minimax Optimization 37

A Single-Loop Accelerated Extra-Gradient Difference Algorith...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Liu, Yuanyuan Shang, Fanhua An, Weixin Liu, Junhao Liu, Hongying Lin, Zhouchen Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University China School of Computer Science and Technology College of Intelligence and Computing Tianjin University China Medical College Tianjin University China National Key Lab of General AI School of Intelligence Science and Technology Peking University China Institute for Artificial Intelligence Peking University China Peng Cheng Laboratory China

ISBN: (纸本)9781713899921

In this paper, we propose a novel extra-gradient difference acceleration algorithm for solving constrained nonconvex-nonconcave (NC-NC) minimax problems. In particular, we design a new extra-gradient difference step to obtain an important quasi-cocoercivity property, which plays a key role to significantly improve the convergence rate in the constrained NC-NC setting without additional structural assumption. Then momentum acceleration is also introduced into our dual accelerating update step. Moreover, we prove that, to find an Ε-stationary point of the function f, the proposed algorithm attains the complexity O(Ε-2) in the constrained NC-NC setting, while the best-known complexity bound is Oe(Ε-4), where Oe(·) hides logarithmic factors compared to O(·). As the special cases of the constrained NC-NC setting, the proposed algorithm can also obtain the same complexity O(Ε-2) for both the nonconvex-concave (NC-C) and convex-nonconcave (C-NC) cases, while the best-known complexity bounds are Oe(Ε-2.5) for the NC-C case and Oe(Ε-4) for the C-NC case. For fair comparison with existing algorithms, we also analyze the complexity bound to find Ε-stationary point of the primal function φ for the constrained NC-C problem, which shows that our algorithm can improve the complexity bound from Oe(Ε-3) to O(Ε-2). To the best of our knowledge, this is the first time that the proposed algorithm improves the best-known complexity bounds from Oe(Ε-4) and Oe(Ε-3) to O(Ε-2) in both the NC-NC and NC-C settings. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Constrained optimization

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：