检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Tang, Bin Liu, Zhengyi Tan, Yacheng He, Qian School of Artificial Intelligence and Big Data Hefei University Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China

The High-Resolution Transformer (HRFormer) can maintain high-resolution representation and share global receptive fields. It is friendly towards salient object detection (SOD) in which the input and output have the same resolution. However, two critical problems need to be solved for two-modality SOD. One problem is two-modality fusion. The other problem is the HRFormer output’s fusion. To address the first problem, a supplementary modality is injected into the primary modality by using global optimization and an attention mechanism to select and purify the modality at the input level. To solve the second problem, a dual-direction short connection fusion module is used to optimize the output features of HRFormer, thereby enhancing the detailed representation of objects at the output level. The proposed model, named HRTransNet, first introduces an auxiliary stream for feature extraction of supplementary modality. Then, features are injected into the primary modality at the beginning of each multi-resolution branch. Next, HRFormer is applied to achieve forwarding propagation. Finally, all the output features with different resolutions are aggregated by intra-feature and inter-feature interactive transformers. Application of the proposed model results in impressive improvement for driving two-modality SOD tasks, e.g., RGB-D, RGB-T, and light field ***://***/liuzywen/HRTransNet Copyright © 2023, The Authors. All rights reserved.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Overview of CCL23-Eval Task 9: Adversarial Robustness Evaluation for Chinese Gaokao Reading Comprehension 22

Overview of CCL23-Eval Task 9: Adversarial Robustness Evalua...

引用

22nd Chinese National Conference on computational Linguistics, CCL 2023

作者： Guo, Yaxin Yan, Guohang Tan, Hongye Li, Ru School of Computer and Information Technology Shanxi University Shanxi Taiyuan030006 China Key Laboratory of Computational Intelligence and Chinese Information Processing Ministry of Education Shanxi University Shanxi Taiyuan030006 China

ISBN: (纸本)9781713889908

The Adversarial Robustness Evaluation for Chinese Gaokao Reading Comprehension Task aims to improve the robustness of machine reading comprehension models in complex and realistic adversarial environments. This task includes four types of adversarial attack strategies: keyword perturbation, Reasoning logic perturbation, Temporal/spatial perturbation, and Cause-effect perturbation. The task constructs an adversarial robust subset called GCRC advRobust. Participants are required to select the correct answer from four options based on the given passage and questions. A total of 29 teams registered for the competition, but due to the high difficulty, only 8 teams submitted their results. All technical information related to this task, including system submissions, official results, and links to supporting resources and software, can be found on the task website1 © 2023 China National Conference on computational Linguistics.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

MRA-Depth: Multi-Resolution Attention based Monocular Depth Estimation

MRA-Depth: Multi-Resolution Attention based Monocular Depth ...

引用

Robotics and Computer Vision (ICRCV), International Conference on

作者： Jing Wen Lukuan Niu School of computer information and technology Key laboratory of computational intelligence and chinese information processing of ministry of education Shanxi University Taiyuan China School of computer information and technology Shanxi University Taiyuan China

Delicate feature would become weaker or even disappear as going through deeper network layer, which results in jagged edges of objects in the depth estimation. To address this problem, we propose a multi-resolution attention based monocular depth estimation by capturing and recalibrating the dependencies of channels between different resolutions, including: we develop a multi-resolution attention encoder by embedding resolution and spatial attention, so as to extract the higher quality features in encoder, and we design a reusable multi-resolution fusion model in decoder, in which different scale features are integrated and then extract multi-resolution attention maps, so as to enhance detail information locally and perspective structure features globally. Experimental results illustrate the proposed network is capable to predict more precise depth and sharper contour, and to outperforms related methods on the KITTI benchmark.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved Optimal Transport Kernel Embedding Method with Gating Mechanism for Singing Voice Separation and Speaker Identification

An Improved Optimal Transport Kernel Embedding Method with G...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Weitao Yuan Yuren Bian Shengbei Wang Masashi Unoki Wenwu Wang Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems Tiangong University China Japan Advanced Institute of Science and Technology Japan Centre for Vision Speech and Signal Processing University of Surrey Guildford UK

Singing voice separation (SVS) and speaker identification (SI) are two classic problems in speech signal processing. Deep neural networks (DNNs) solve these two problems by extracting effective representations of the target signal from the input mixture. Since essential features of a signal can be well reflected on its latent geometric structure of the feature distribution, a natural way to address SVS/SI is to extract the geometry-aware and distribution-related features of the target signal. To do this, this work introduces the concept of optimal transport (OT) to SVS/SI and proposes an improved optimal transport kernel embedding (iOTKE) to extract the target-distribution-related features. The iOTKE learns an OT from the input signal to the target signal on the basis of a reference set learned from all training data. Thus it can maintain the feature diversity and preserve the latent geometric structure of the distribution for the target signal. To further improve the feature selection ability, we extend the proposed iOTKE to a gated version, i.e., gated iOTKE (G-iOTKE), by incorporating a lightweight gating mechanism. The gating mechanism controls effective information flow and enables the proposed method to select important features for a specific input signal. We evaluated the proposed G-iOTKE on SVS/SI. Experimental results showed that the proposed method provided better results than other models.

关键词： Deep learning Neural networks Training data Logic gates signal processing Feature extraction Data mining

来源：评论

学校读者我要写书评

暂无评论

Fuzzy learning machine 22

Fuzzy learning machine

引用

Proceedings of the 36th International Conference on Neural Information processing Systems

作者： Junbiao Cui Jiye Liang Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education School of Computer and Information Technology Shanxi University Taiyuan Shanxi China

ISBN: (纸本)9781713871088

Classification is one of the most important problems in machine learning and the nature of it is concept cognition. So far, dozens of different classifiers have been designed. Although their working mechanisms vary widely, few of them fully consider concept cognition. In this paper, a new learning machine, fuzzy learning machine (FLM), is proposed from the perspective of concept cognition. Inspired by cognitive science, its working mechanism is of strong interpretability. At the same time, FLM roots in set theory and fuzzy set theory, so FLM has a solid mathematical foundation. The systematic experimental results on a large number of data sets show that FLM can achieve excellent performance, even with the simple implementation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A spectrum-enhanced attention model for semantic segmentation of remote sensing images

A spectrum-enhanced attention model for semantic segmentatio...

引用

2025 IEEE International Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Li, Xin Xu, Feng Tao, Feifei Tong, Yao Lyu, Xin Zhong, Jianyi Kaup, André College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology Ministry of Water Resources Hohai University Nanjing China School of Computer Engineering Jiangsu Ocean University Lianyungang China School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China Multimedia Communications and Signal Processing Friedrich-Alexander University Erlangen-Nuremberg Erlangen Germany

ISBN: (纸本)9798350368741

Semantic segmentation of remote sensing images (RSIs) is essential for applications such as environmental monitoring, urban planning, and disaster management. Convolutional Neural Networks (CNNs) and their variants struggle to capture comprehensive spectral context for learning discriminative representations. In this paper, we propose a Spectrum-Enhanced Network (SPENet) that leverages the Frequency Transformer Block (FTB) to capture rich spectral context. FTB integrates Spectrum-Enhanced Attention (SEA) with Multi-Head Frequency Self-Attention (MH-FSA), incorporating more informative contextual cues. Specifically, SEA aggregates spectral statistics through covariance matrix normalization before applying channel-wise attention. By projecting feature maps onto the frequency domain, MH-FSA provides the network with a broader context, extending beyond the low-frequency focus of standard self-attention mechanisms. Extensive experiments on the ISPRS Potsdam and LoveDA datasets show that SPENet significantly outperforms state-of-the-art methods. Besides, the proposed SEA module notably rises average F1-score/overall accuracy/mean insert over union wiht more than 2.5/2.6%/2.3%, as demonstrated by ablation study. © 2025 IEEE.

关键词： frequency transformer remote sensing images Semantic segmentation spectrum enhancement

来源：评论

学校读者我要写书评

暂无评论

Point, Segment and Count: A Generalized Framework for Object Counting

Point, Segment and Count: A Generalized Framework for Object...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhizhong Huang Mingliang Dai Yi Zhang Junping Zhang Hongming Shan Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China School of Cyber Science and Engineering Sichuan University Chengdu China Frontiers Center for Brain Science Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Institute of Science and Technology for Brain-inspired Intelligence & MOE Fudan University Shanghai China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Class-agnostic object counting aims to count all objects in an image with respect to example boxes or class names, a.k.a few-shot and zero-shot counting. In this paper, we propose a generalized framework for both few-shot and zero-shot object counting based on detection. Our framework combines the superior advantages of two foundation models without compromising their zero-shot capability: (i) SAM to segment all possible objects as mask proposals, and (ii) CLIP to classify proposals to obtain accurate object counts. However, this strategy meets the obstacles of efficiency over-head and the small crowded objects that cannot be localized and distinguished. To address these issues, our framework, termed PseCo, follows three steps: point, segment, and count. Specifically, we first propose a class-agnostic object localization to provide accurate but least point prompts for SAM, which consequently not only reduces computation costs but also avoids missing small objects. Furthermore, we propose a generalized object classification that leverages CLIP image/text embeddings as the classifier, following a hierarhical knowledge distillation to obtain discriminative classifications among hierarchical mask proposals. Extensive experimental results on FSC-147, COCO, and LVIS demonstrate that PseCo achieves state-of-the-art performance in both few-shot/zero-shot object counting/detection.

关键词： Location awareness Image segmentation Computer vision Accuracy Costs Power capacitors Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

DSPE: An End-to-End Drug Synergy Combination Prediction Algorithm for Echinococcosis

引用

Current Bioinformatics 2025年

作者： Li, Haitao Jiang, Liyuan Chu, Yuanyuan Liu, Yuansheng Zheng, Chunhou Su, Yansen Key Laboratory of Intelligent Computing and Signal Processing School of Artificial Intelligence Anhui University 111 Jiulong Road Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center 5089 Wangjiang West Road Anhui Hefei230088 China College of Computer Science and Electronic Engineering Hunan University China

Background: Echinococcosis, a parasitic disease caused by the larvae of the Echinococcus parasite, poses a serious threat to human health. Medication is an indispensable means of treatment for Echinococcosis;however, due to the less satisfactory efficacy of single drugs, identifying effective drug combinations for the treatment of Echinococcosis is essential. Yet, current predictive models for drug synergy in Echinococcosis face accuracy challenges due to data scarcity, method limitations, and insufficient feature representation. Objective: This work aims to design an end-to-end method to predict drug synergistic combinations, which enables efficient and accurate identification of drug combinations against Echinococcosis. Methods: In this work, an end-to-end method, named DSPE, is proposed for predicting anti-Echinococcosis drug synergistic combinations. In DSPE, a dataset of Echinococcosis drug synergistic combinations is constructed by retrieving and extracting information from related scientific articles. Further, DSPE employs a residual graph attention network to deeply analyze drug characteristics and their interactions, thereby enhancing the performance of deep learning models. It also explores the protein-protein interaction network related to Echinococcosis, using node2vec combined with an attention mechanism to efficiently encode disease features. Finally, it predicts the synergy of drug combinations based on the Bliss score by integrating drug combinations and disease features. Results: Experimental evidence shows that DSPE outperforms five state-of-the-art algorithms in predicting drug combination effects by leveraging disease-target information and single-agents for the treatment. Conclusion: DSPE improves prediction accuracy and addresses the issue of data scarcity for new diseases, offering new insights and methods for the development of treatment plans for parasitic diseases in the future. © 2025 Bentham Science Publishers.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Speaker Recognition Based on Pre-Trained Model and Deep Clustering

Speaker Recognition Based on Pre-Trained Model and Deep Clus...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Liang He Zhida Song Shuanghong Liu Mengqi Niu Ying Hu Hao Huang School of Computer Science and Technology Xinjiang University Urumqi China School of Intelligence Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China Department of Electronic Engineering Tsinghua University Beijing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

In this paper, we propose a novel loss by integrating a deep clustering (DC) loss at the frame-level and a speaker recognition loss at the segment-level into a single network without additional data requirements and exhaustive computation. The DC loss implicitly generates soft pseudo-phoneme labels for each frame-level feature, which facilitates extracting more discriminant speaker representation by suppressing phonetic content information. We study the DC loss not only on the acoustic feature, but also on the features extracted by the pre-trained models, such as wav2vec 2.0, HuBERT and WavLM. Experimental results on the VoxCeleb dataset shows that the overall system performance based on the pre-trained model features are better than the one on the acoustic feature. The proposed loss is significantly effective for systems on the acoustic feature and has a marginal improvement for systems on the pre-trained model feature.

关键词： Training Costs computational modeling System performance Phonetics Multimedia databases Feature extraction

来源：评论

学校读者我要写书评

暂无评论

SC-RegNet: Unsupervised Self-Calibrated 3D Biomedical Image Registration Network

SC-RegNet: Unsupervised Self-Calibrated 3D Biomedical Image ...

引用

Chinese Automation Congress (CAC)

作者： Jian Yang Jun Wu Rui Zhang Meng Wang Yujie Tang Lei Qu Key Laboratory of Computational Intelligence and Signal Processing Ministry of Education School of Electronics and Information Engineering Anhui University (AHU) Hefei China

ISBN: (数字)9781665426473

ISBN: (纸本)9781665426480

Deformable image registration is critical in many biomedical image analysis tasks. Traditional registration algorithms involve a time-consuming iterative optimization process. Most deep learning-based registration networks follow the U-Net shape encoding-decoding architecture, and their downsampling layers are shallow, making it difficult to obtain sufficient semantic information with a small receptive field. In this work, we extend the self-calibrated convolution applied to tasks such as 2D target detection to the encoding stage of 3D image registration networks. The proposed SC-RegNet can get more semantic information to make up for the existing registration networks in an unsupervised training manner while not introducing additional parameters. We evaluated SC-RegNet on two public available human Brain MRI datasets: LPBA40 and IBSR18, and a private mouse brain dataset. The experimental results show the superiority of SC-RegNet over the SOTA image registration methods with no extra time-consuming.

关键词： Training Image registration Three-dimensional displays Convolution Shape Semantics Object detection

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：