检索结果-内蒙古大学图书馆

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Weizhao Zhang, Yang Zhuo, Wei Shen, Linlin Yang, Jiaqi Deng, Songhe Sun, Liang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China School of Computer Science University of Nottingham China

Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and their performances degrade significantly while applied to a distinct domain. To this end, we propose to leverage the cutting-edge foundation model, the Segment Anything Model (SAM), for generalization enhancement. The SAM however performs unsatisfactorily on domains that are distinct from its training data, which primarily comprise natural scene images, and it does not support automatic segmentation of specific semantics due to its interactive prompting mechanism. In our work, we introduce APSeg, a novel auto-prompt network for cross-domain few-shot semantic segmentation (CD-FSS), which is designed to be auto-prompted for guiding cross-domain segmentation. Specifically, we propose a Dual Prototype Anchor Transformation (DPAT) module that fuses pseudo query prototypes extracted based on cycle-consistency with support prototypes, allowing features to be transformed into a more stable domain-agnostic space. Additionally, a Meta Prompt Generator (MPG) module is introduced to automatically generate prompt embeddings, eliminating the need for manual visual prompts. We build an efficient model which can be applied directly to target domains without fine-tuning. Extensive experiments on four cross-domain datasets show that our model outperforms the state-of-the-art CD-FSS method by 5.24% and 3.10% in average accuracy on 1-shot and 5-shot settings, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lin, Zhenchao He, Li Yang, Hongqiang Sun, Xiaoqun Zhang, Guojin Chen, Weinan Guan, Yisheng Zhang, Hong School of Electromechanical Engineering Guangdong University of Technology Guangzhou China Department of Electronic and Electrical Engineering Southern University of Science and Technology China Shenzhen Key Laboratory of Robotics and Computer Vision China Meituan Technology Co. Ltd Shenzhen China

Large-scale point cloud consists of a multitude of individual objects, thereby encompassing rich structural and underlying semantic contextual information, resulting in a challenging problem in efficiently segmenting a point cloud. Most existing researches mainly focus on capturing intricate local features without giving due consideration to global ones, thus failing to leverage semantic context. In this paper, we propose a Similarity-Weighted Convolution and local-global Fusion Network, named SWCF-Net, which takes into account both local and global features. We propose a Similarity-Weighted Convolution (SWConv) to effectively extract local features, where similarity weights are incorporated into the convolution operation to enhance the generalization capabilities. Then, we employ a downsampling operation on the K and V channels within the attention module, thereby reducing the quadratic complexity to linear, enabling Transformer to deal with large-scale point cloud. At last, orthogonal components are extracted in the global features and then aggregated with local features, thereby eliminating redundant information between local and global features and consequently promoting efficiency. We evaluate SWCF-Net on large-scale outdoor datasets SemanticKITTI and Toronto3D. Our experimental results demonstrate the effectiveness of the proposed network. Our method achieves a competitive result with less computational cost, and is able to handle large-scale point clouds efficiently. The code is available at https://***/Sylva-Lin/SWCF-Net Copyright © 2024, The Authors. All rights reserved.

关键词： Convolution

Shearlet-Based Structure-Aware Filtering for Hyperspectral and LiDAR Data Classification

学校读者我要写书评

暂无评论

Journal of Remote Sensing 2021年第1期2021卷 237-261页

作者： Sen Jia Zhangwei Zhan Meng Xu College of Computer Science and Software Engineering Shenzhen UniversityShenzhenChina Key Laboratory for Geo-Environmental Monitoring of Coastal Zone of the Ministry of Natural Resources Shenzhen UniversityShenzhenChina SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for SocietyShenzhenChina

The joint interpretation of hyperspectral images(HSIs)and light detection and ranging(LiDAR)data has developed rapidly in recent years due to continuously evolving image processing ***,most feature extraction methods are carried out by convolving the raw data with fixed-size filters,whereas the structural and texture information of objects in multiple scales cannot be sufficiently *** this article,a shearlet-based structure-aware filtering approach,abbreviated as ShearSAF,is proposed for HSI and LiDAR feature extraction and ***,superpixel-guided kernel principal component analysis(KPCA)is firstly adopted on raw HSIs to reduce the ***,the KPCA-reduced HSI and LiDAR data are converted to the shearlet domain for texture and area feature *** contrast,superpixel segmentation algorithm utilizes the raw HSI data to obtain the initial oversegmentation ***,by utilizing a well-designed minimum merging cost that fully considers spectral(HSI and LiDAR data),texture,and area features,a region merging procedure is gradually conducted to produce a final merging ***,a scale map that locally indicates the filter size is achieved by calculating the edge ***,the KPCA-reduced HSI and LiDAR data are convolved with the locally adaptive filters for feature extraction,and a random forest(RF)classifier is thus adopted for *** effectiveness of our ShearSAF approach is verified on three real-world datasets,and the results show that the performance of ShearSAF can achieve an accuracy higher than that of comparison methods when exploiting small-size training sample *** codes of this work will be available at http://***/papers/for the sake of reproducibility.

关键词： LiDAR Shear utilize

Perspective Phase Angle Model for Polarimetric 3D Reconstruction

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Guangcheng He, Li Guan, Yisheng Zhang, Hong Guangdong University of Technology Guangzhou China Southern University of Science and Technology Shenzhen China Shenzhen Key Laboratory of Robotics and Computer Vision China

Current polarimetric 3D reconstruction methods, including those in the well-established shape from polarization literature, are all developed under the orthographic projection assumption. In the case of a large field of view, however, this assumption does not hold and may result in significant reconstruction errors in methods that make this assumption. To address this problem, we present the perspective phase angle (PPA) model that is applicable to perspective cameras. Compared with the orthographic model, the proposed PPA model accurately describes the relationship between polarization phase angle and surface normal under perspective projection. In addition, the PPA model makes it possible to estimate surface normals from only one single-view phase angle map and does not suffer from the so-called π-ambiguity problem. Experiments on real data show that the PPA model is more accurate for surface normal estimation with a perspective camera than the orthographic model. Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

Poster: Towards Accurate and Fast Federated Learning in End-Edge-Cloud Orchestrated Networks 43

学校读者我要写书评

暂无评论

Poster: Towards Accurate and Fast Federated Learning in End-...

43rd IEEE International Conference on Distributed Computing Systems, ICDCS 2023

作者： Li, Mingze Sun, Peng Zhou, Huan Zhao, Liang Liu, Xuxun Leung, Victor C. M. College of Computer and Information Technology China Three Gorges University Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering Yichang China College of Computer Science and Electronic Engineering Hunan University Changsha China College of Electronic and Information Engineering South China University of Technology Guangzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9798350339864

This work proposes a novel three-layer federated learning (FL) framework with parameter selection and pre-synchronization (PSPFL) to achieve fast and accurate model training. The basic idea of PSPFL is that clients select partial model parameters for transmission and then base stations aggregate them cooperatively (i.e., pre-synchronization) and send the aggregated results to the server for global model update periodically. However, there is an intrinsic trade-off between parameter transmission overhead and model training loss. To strike a desirable balance between them, we investigate the optimal parameter pre-synchronization round and local training round under PSPFL. Specifically, we propose a Deep Q-Network (DQN)-based method to obtain the local training round and parameter pre-synchronization round. Finally, extensive experiments are conducted to evaluate the performance of the proposed method on commonly used datasets. The results show that the proposed method can reduce the sum of FL completion time and training loss by an average of 8.17%-18.82% compared to benchmarks. © 2023 IEEE.

关键词： Synchronization

CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Xu Hou, XianXu Lai, Zhihui Zhou, Jie Zhang, Ya-Nan Pedrycz, Witold Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China The Department of Electrical & Computer Engineering University of Alberta University of Alberta Canada

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations;(2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

Ontology-Based BERT Model for Automated Information Extraction from Geological Hazard Reports

学校读者我要写书评

暂无评论

Journal of Earth Science 2023年第5期34卷 1390-1405页

作者： Kai Ma Miao Tian Yongjian Tan Qinjun Qiu Zhong Xie Rong Huang Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges UniversityYichang 443002China College of Computer and Information Technology China Three Gorges UniversityYichang 443002China Hubei Engineering Technology Research Center for Farmland Environment Monitoring China Three Gorges UniversityYichang 443002China School of Computer Science China University of GeosciencesWuhan 430074China Key Laboratory of Urban Land Resources Monitoring and Simulation Ministry of Natural ResourcesShenzhen 518034China Beijing Key Laboratory of Urban Spatial Information Engineering Beijing 100045China College of Economics and Management China Three Gorges UniversityYichang 443002China

Geological knowledge can provide support for knowledge discovery, knowledge inference and mineralization predictions of geological big data. Entity identification and relationship extraction from geological data description text are the key links for constructing knowledge graphs. Given the lack of publicly annotated datasets in the geology domain, this paper illustrates the construction process of geological entity datasets, defines the types of entities and interconceptual relationships by using the geological entity concept system, and completes the construction of the geological corpus. To address the shortcomings of existing language models(such as Word2vec and Glove) that cannot solve polysemous words and have a poor ability to fuse contexts, we propose a geological named entity recognition and relationship extraction model jointly with Bidirectional Encoder Representation from Transformers(BERT) pretrained language model. To effectively represent the text features, we construct a BERT-bidirectional gated recurrent unit network(BiGRU)-conditional random field(CRF)-based architecture to extract the named entities and the BERT-BiGRU-Attention-based architecture to extract the entity relations. The results show that the F1-score of the BERT-BiGRU-CRF named entity recognition model is 0.91 and the F1-score of the BERT-BiGRU-Attention relationship extraction model is 0.84, which are significant performance improvements when compared to classic language models(e.g., word2vec and Embedding from Language Models(ELMo)).

关键词： ontology BERT model name entity recognition relation extraction knowledge graph

Image saliency detection method based on multi-feature maps fusion 4

学校读者我要写书评

暂无评论

Image saliency detection method based on multi-feature maps ...

4th International Conference on computer Graphics, Image, and Virtualization, ICCGIV 2024

作者： Li, Xiaoli Liu, Yunpeng Zhao, Huaici Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Key Laboratory of Opto-Electronic Information Processing Shenyang China The Key Lab of Image Understanding and Computer Vision Shenyang China Shenyang Jianzhu University Shenyang China

ISBN: (纸本)9781510683242

In this research, we introduce an innovative saliency detection algorithm, comprising three essential steps. Firstly, leveraging fully convolutional networks with aggregation interaction modules, we generate an initial saliency map. Secondly, we extract hand-craft and deep features to express the image, then use manifold ranking method to construct saliency maps. Ultimately, by integrating the outcomes from preceding stages, we generate the final saliency map. Experimental findings demonstrate that our method surpasses twelve cutting-edge saliency detection techniques in terms of precision, recall, F-measure, and MAE value metrics." © 2024 SPIE.

关键词： Feature extraction

A New Dynamic Routing Network for Monocular Depth Estimation 12

学校读者我要写书评

暂无评论

A New Dynamic Routing Network for Monocular Depth Estimation

12th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2022

作者： Luo, Zhehao Luo, Sijin Liang, Guoyuan Wu, Xinyu Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Province Shenzhen China University of Chinese Academy of Sciences Beijing China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Chinese Academy of Sciences Guangdong Province Shenzhen China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Province Shenzhen China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

Depth estimation is an essential task for understanding the geometry of 3D scenes. Compared with multi-view-based methods, monocular depth estimation is more challenging for the requirement of integrating not only global information but also local cues from various parts. Recently, numerous Convolutional Neural Networks (CNNs) based approaches relying on pre-defined static architectures have been reported. Although many of them have achieved remarkable improvements in accuracy, there remains problem with the generality of the static model when it comes to diverse scenes. In this paper, a novel deep network with dynamic routing architecture is proposed with a dynamically adjustable structure with respect to different inputs, therefore leading to not only improvements on both accuracy and generality but also decrease of the model parameters. Extensive experiments of monocular depth estimation have been conducted on two well-known challenging datasets (i.e., NYUD-v2 and Make3D) as well as the mixed dataset, and have verified the effectiveness of the proposed dynamic framework. © 2022 IEEE.

关键词： Deep neural networks