检索结果-内蒙古大学图书馆

3D RoI-aware U-net for accurate and efficient colorectal tumor segmentation

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Huang, Yi-Jie Dou, Qi Wang, Zi-Xian Liu, Li-Zhi Jin, Ying Li, Chao-Feng Wang, Lisheng Chen, Hao Xu, Rui-Hua Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University China Imsight Medical Technology Co. Ltd. China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Sun Yat-sen University Cancer Center State Key Laboratory of Oncology in South China Collaborative Innovation Center for Cancer Medicine Guangzhou China

Segmentation of colorectal cancerous regions from 3D Magnetic Resonance (MR) images is a crucial procedure for radiotherapy which conventionally requires accurate delineation of tumour boundaries at an expense of labor, time and reproducibility. While deep learning based methods serve good baselines in 3D image segmentation tasks, small applicable patch size limits effective receptive field and degrades segmentation performance. In addition, Regions of interest (RoIs) localization from large whole volume 3D images serves as a preceding operation that brings about multiple benefits in terms of speed, target completeness, reduction of false positives. Distinct from sliding window or non-joint localization-segmentation based models, we propose a novel multitask framework referred to as 3D RoI-aware U-Net (3D RU-Net), for RoI localization and in-region segmentation where the two tasks share one backbone encoder network. With the region proposals from the encoder, we crop multi-level RoI in-region features from the encoder to form a GPU memory-efficient decoder for detail-preserving segmentation and therefore enlarged applicable volume size and effective receptive field. To effectively train the model, we designed a Dice formulated loss function for the global-to-local multi-task learning procedure. Based on the efficiency gains demonstrated by the proposed method, we went on to ensemble models with different receptive fields to achieve even higher performance costing minor extra computational expensiveness. Extensive experiments were subsequently conducted on 64 cancerous cases with a four-fold cross-validation, and the results showed significant superiority in terms of accuracy and efficiency over conventional state-of-the art frameworks. In conclusion, the proposed method has a huge potential for extension to other 3D object segmentation tasks from medical images due to its inherent generalizability. The code for the proposed method is publicly available. Copyright ©

关键词： Signal encoding

Incremental transformer with deliberation decoder for document grounded conversations

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Li, Zekang Niu, Cheng Meng, Fandong Feng, Yang Li, Qian Zhou, Jie Dian Group School of Electronic Information and Communications Huazhong University of Science and Technology Pattern Recognition Center WeChat AI Tencent Inc China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences School of Computer Science and Engineering Northeastern University China

Document Grounded Conversations is a task to generate dialogue responses when chatting about the content of a given document. Obviously, document knowledge plays a critical role in Document Grounded Conversations, while existing dialogue models do not exploit this kind of knowledge effectively enough. In this paper, we propose a novel Transformerbased architecture for multi-turn document grounded conversations. In particular, we devise an Incremental Transformer to encode multi-turn utterances along with knowledge in related documents. Motivated by the human cognitive process, we design a two-pass decoder (Deliberation Decoder) to improve context coherence and knowledge correctness. Our empirical study on a real-world Document Grounded Dataset proves that responses generated by our model significantly outperform competitive baselines on both context coherence and knowledge relevance. Copyright © 2019, The Authors. All rights reserved.

关键词： Decoding

Tasks integrated networks: Joint detection and retrieval for image search

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Lei He, Zhenwei Yang, Yi Wang, Liang Gao, Xinbo School of Microelectronics and Communication Engineering Chongqing University Chongqing400044 China Center for Artificial Intelligence University of Technology Sydney Australia National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing400065 China

The traditional object (person) retrieval (re-identification) task aims to learn a discriminative feature representation with intra-similarity and inter-dissimilarity, which supposes that the objects in an image are manually or automatically pre-cropped exactly. However, in many real-world searching scenarios (e.g., video surveillance), the objects (e.g., persons, vehicles, etc.) are seldom accurately detected or annotated. Therefore, object-level retrieval becomes intractable without bounding-box annotation, which leads to a new but challenging topic, i.e. image-level search with multi-task integration of joint detection and retrieval. In this paper, to address the image search issue, we first introduce an end-to-end Integrated Net (I-Net), which has three merits: 1) A Siamese architecture and an on-line pairing strategy for similar and dissimilar objects in the given images are designed. Benefited by the Siamese structure, I-Net learns the shared feature representation, because, on which, both object detection and classification tasks are handled. 2) A novel on-line pairing (OLP) loss is introduced with a dynamic feature dictionary, which alleviates the multi-task training stagnation problem, by automatically generating a number of negative pairs to restrict the positives. 3) A hard example priority (HEP) based softmax loss is proposed to improve the robustness of classification task by selecting hard categories. The shared feature representation of I-Net may restrict the task-specific flexibility and learning capability between detection and retrieval tasks. Therefore, with the philosophy of divide and conquer, we further propose an improved I-Net, called DC-I-Net, which makes two new contributions: 1) two modules are tailored to handle different tasks separately in the integrated framework, such that the task specification is guaranteed. 2) A class-center guided HEP loss (C2HEP) by exploiting the stored class centers is proposed, such that the intra-similarity a

关键词： Object recognition

Local Neighbor Propagation on Graphs for Robust Feature Matching

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Guo, Hanlin Xiao, Guobao Su, Lumei Zhou, Jiaxing Wang, Dahan Xiamen Key Laboratory of Frontier Electric Power Equipment and Intelligent Control School of Electrical Engineering and Automation Xiamen University of Technology China Fujian Key Laboratory of Sensing and Computing for Smart Cities School of Information Science and Engineering Xiamen University China College of Computer and Control Engineering Minjiang University China Fujian Key Laboratory of Pattern Recognition and Image Understanding School of Computer and Information Engineering Xiamen University of Technology China

Establishing reliable correspondences between two sets of feature points is a critical preprocessing step in many computer vision and pattern recognition tasks. In this paper, we propose a novel robust Local Neighbor Propagation on Graphs based feature matching (LNPG) method, to obtain good correspondences for feature matching. LNPG starts from a novel neighborhood graph construction strategy. The strategy leverages the spatial consistency constraint to generate a series of neighborhood sets, and employs the residual information to preserve the local neighborhood relationships of potential inliers (i.e., true matches). Subsequently, LNPG incorporates local neighbor propagation into the graph to enhance connections between data in different neighborhoods, by using the path-based similarity measurement and the adaptive graph partition. In addition, LNPG includes a novel consistency-filtering-based clustering algorithm for robust feature matching. This clustering algorithm introduces a reliable neighborhood consistency measure function and an effective cluster merging criterion for cluster detection and cluster merging during the clustering process, respectively. Overall, LNPG not only effectively distinguishes inliers from outliers, but also reliably classifies inliers into different transformation models between pairs of images. Experiments on publicly available datasets with different types of image transformations show the superiority of our LNPG in comparison with other state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Clustering algorithms

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Wenkai Bi, Xiaohan Lin, Yankai Chen, Sishuo Zhou, Jie Sun, Xu Gaoling School of Artificial Intelligence Renmin University of China Beijing China Center for Data Science Peking University China Pattern Recognition Center WeChat AI Tencent Inc. China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China

Driven by the rapid development of Large Language Models (LLMs), LLM-based agents have been developed to handle various real-world applications, including finance, healthcare, and shopping, etc. It is crucial to ensure the reliability and security of LLM-based agents during applications. However, the safety issues of LLM-based agents are currently under-explored. In this work, we take the first step to investigate one of the typical safety threats, backdoor attack, to LLM-based agents. We first formulate a general framework of agent backdoor attacks, then we present a thorough analysis of different forms of agent backdoor attacks. Specifically, compared with traditional backdoor attacks on LLMs that are only able to manipulate the user inputs and model outputs, agent backdoor attacks exhibit more diverse and covert forms: (1) From the perspective of the final attacking outcomes, the agent backdoor attacker can not only choose to manipulate the final output distribution, but also introduce the malicious behavior in an intermediate reasoning step only, while keeping the final output correct. (2) Furthermore, the former category can be divided into two subcategories based on trigger locations, in which the backdoor trigger can either be hidden in the user query or appear in an intermediate observation returned by the external environment. We implement the above variations of agent backdoor attacks on two typical agent tasks including web shopping and tool utilization. Extensive experiments show that LLM-based agents suffer severely from backdoor attacks and such backdoor vulnerability cannot be easily mitigated by current textual backdoor defense algorithms. This indicates an urgent need for further research on the development of targeted defenses against backdoor attacks on LLM-based agents.3 Warning: This paper may contain biased content. © 2024, CC BY.

关键词：

Lower bounds on some van der waerden numbers based on quadratic residues

学校读者我要写书评

暂无评论

Journal of Combinatorial Mathematics and Combinatorial Computing 2012年 83卷 23-31页

作者： Liang, Meilian Xu, Xiaodong Shao, Zehui Xiu, Baoxin School of Mathematics and Information Science Guangxi University Nanning 530004 China Guangxi Academy of Sciences Nanning 530007 China Key Laboratory of Pattern Recognition and Intelligent Information Processing School of Information Science and Technology Chengdu University Chengdu 610106 China College of Information System and Management National University of Defense Technology Changsha 410073 China

The van der Waerden number W(r, k) is the least integer N such that every r-coloring of {1,2, • • •, N} contains a monochromatic arithmetic progression of length at least k. Rabung gave a method to obtain lower bounds on W(2,k) based on quadratic residues, and performed computations on all primes no greater than 20117. By improving the efficiency of the algorithm of Rabung, we perform the computation for all primes up to 6 x 107, and obtain lower bounds on W(2, k) for k between 11 and 23.

关键词： Computational efficiency

MARL-based calibration for cameras with large FOV

学校读者我要写书评

暂无评论

Optica Acta: International Journal of Optics 2024年第1-3期71卷

作者： Xinyu Yang Fuhan Chen Jingwen Jiang Hui Xie Qiaofeng Ou Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition School of Information Engineering Nanchang Hangkong University Nanchang People’s Republic of China

Achieving high-precision measurements in a large field of view (FOV) is a challenging task. The accuracy of vision measurements is determined by the quality of camera calibration, which is influenced by the pose of the target. To obtain suitable target pose, a target pose optimization method based on multi-agent reinforcement learning (MARL) is proposed. Firstly, the target pose optimization problem is modelled as a Markov decision process (MDP). Secondly, a multi-agent proximal policy optimization (MAPPO) algorithm for target pose optimization is designed by parameter sharing mechanism. Finally, optimization algorithm is adopted to camera calibration process. The calibration experiment was carried out under the large FOV of 4600 mm × 2300 mm. The results show that the back-projection error was 0.198 mm, the relative error of the diagonal length of target (505.847 mm) was 0.789 mm, and the success rate of large FOV camera calibration was 98.5%.

关键词： Camera calibration large FOV target pose optimization MARL MDP MAPPO

A Parallel-based Lifting Algorithm and VLSI Architecture for DWT

学校读者我要写书评

暂无评论

Journal of Electronics(China) 2006年第2期23卷 244-248页

作者： Xiong Chengyi Tian Jinwen Liu Jian Gao Zhirong The State Key Lab of Education Commission for Image Processing and Intelligent Control Institute of Pattern Recognition ＆ Artificial Intelligence Huazhong Univ. of Science ＆ Tech. Wuhan 430074 China College of Electronic Info. Eng. South- Center Univ. for Nationalities Wuhan 430074 China Dept of Computer Science Wuhan Univ. of Science ＆ Eng. Wuhan 430074 China

A novel Parallel-Based Lifting Algorithm （PBLA） for Discrete Wavelet Transform （DWT）, exploiting the parallelism of arithmetic operations in all lifting steps, is proposed in this paper. It leads to reduce the critical path latency of computation, and to reduce the complexity of hardware implementation as well. The detailed derivation on the proposed algorithm, as well as the resulting Very Large Scale Integration （VLSI） architecture, is introduced, taking the 9/7 DWT as an example but without loss of generality. In comparison with the Conventional Lifting Algorithm Based Implementation （CLABI）, the critical path latency of the proposed architecture is reduced by more than half from （4Tm ＋ 8Ta）to Tm ＋ 4Ta, and is competitive to that of Convolution-Based Implementation （CBI）, but the new implementation will save significantly in hardware. The experimental results demonstrate that the proposed architecture has good performance in both increasing working frequency and reducing area.

关键词： Discrete Wavelet Transform （DFT） Lifting scheme Parallel Very Large Scale Integration（VLSI）

Translatotron-V(ison): An End-to-End Model for In-image Machine Translation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lan, Zhibin Niu, Liqiang Meng, Fandong Zhou, Jie Zhang, Min Su, Jinsong School of Informatics Xiamen University China Pattern Recognition Center WeChat AI Tencent Inc China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Xiamen University Ministry of Culture and Tourism China Institute of Computer Science and Technology Soochow University China

In-image machine translation (IIMT) aims to translate an image containing texts in source language into an image containing translations in target language. In this regard, conventional cascaded methods suffer from issues such as error propagation, massive parameters, and difficulties in deployment and retaining visual characteristics of the input image. Thus, constructing end-to-end models has become an option, which, however, faces two main challenges: 1) the huge modeling burden, as it is required to simultaneously learn alignment across languages and preserve the visual characteristics of the input image;2) the difficulties of directly predicting excessively lengthy pixel sequences. In this paper, we propose Translatotron-V(ision), an end-to-end IIMT model consisting of four modules. In addition to an image encoder, and an image decoder, our model contains a target text decoder and an image tokenizer. Among them, the target text decoder is used to alleviate the language alignment burden, and the image tokenizer converts long sequences of pixels into shorter sequences of visual tokens, preventing the model from focusing on low-level visual features. Besides, we present a two-stage training framework for our model to assist the model in learning alignment across modalities and languages. Finally, we propose a location-aware evaluation metric called Structure-BLEU to assess the translation quality of the generated images. Experimental results demonstrate that our model achieves competitive performance compared to cascaded models with only 70.9% of parameters, and significantly outperforms the pixel-level end-to-end IIMT model. Copyright © 2024, The Authors. All rights reserved.

关键词： Pixels