检索结果-内蒙古大学图书馆

Perceptive self-supervised learning network for noisy image watermark removal

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tian, Chunwei Zheng, Menghua Li, Bo Zhang, Yanning Zhang, Shichao Zhang, David School of Software Northwestern Polytechnical University Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China School of Electronics and Information Northwestern Polytechnical University Xi’an710129 China School of Computer Science Northwestern Polytechnical University National Engineering Laboratory for Integrated AeroSpace-Ground-Ocean Big Data Application Technology Xi’an710129 China Guangxi Key Lab of Multisource Information Mining & Security College of Computer Science & Engineering Guangxi Normal University Guilin541004 China Shenzhen518172 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China

Popular methods usually use a degradation model in a supervised way to learn a watermark removal model. However, it is true that reference images are difficult to obtain in the real world, as well as collected images by cameras suffer from noise. To overcome these drawbacks, we propose a perceptive self-supervised learning network for noisy image watermark removal (PSLNet) in this paper. PSLNet depends on a parallel network to remove noise and watermarks. The upper network uses task decomposition ideas to remove noise and watermarks in sequence. The lower network utilizes the degradation model idea to simultaneously remove noise and watermarks. Specifically, mentioned paired watermark images are obtained in a self-supervised way, and paired noisy images (i.e., noisy and reference images) are obtained in a supervised way. To enhance the clarity of obtained images, interacting two sub-networks and fusing obtained clean images are used to improve the effects of image watermark removal in terms of structural information and pixel enhancement. Taking into texture information account, a mixed loss uses obtained images and features to achieve a robust model of noisy image watermark removal. Comprehensive experiments show that our proposed method is very effective in comparison with popular convolutional neural networks (CNNs) for noisy image watermark removal. Codes can be obtained at https://***/hellloxiaotian/PSLNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Image denoising

学校读者我要写书评

暂无评论

Sets clustering

arXiv 2020年

作者： Jubran, Ibrahim Tukan, Murad Maalouf, Alaa Feldman, Dan Robotics and Big Data Lab Department of Computer Science University of Haifa Israel

The input to the sets-k-means problem is an integer k ≥ 1 and a set P = {P1;Pn} of sets in Rd. The goal is to compute a set C of k centers (points) in Rd that minimizes the sum Σ P2P minp2P;c2C p - c2 of squared distances to these sets. An ϵ-core-set for this problem is a weighted subset of P that approximates this sum up to 1 ± ϵ factor, for every set C of k centers in Rd. We prove that such a core-set of O(log2 n) sets always exists, and can be computed in O(n log n) time, for every input P and every fixed d;k ≥ 1 and ϵ 2 (0;1). The result easily generalized for any metric space, distances to the power of z > 0, and M-estimators that handle outliers. Applying an inefficient but optimal algorithm on this coreset allows us to obtain the first PTAS (1 + ϵ approximation) for the sets-k- means problem that takes time near linear in n. This is the first result even for sets-mean on the plane (k = 1, d = 2). Open source code and experimental results for document classification and facility locations are also provided. Copyright © 2020, The Authors. All rights reserved.

关键词： Open systems

NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lin, Bingqian Nie, Yunshuang Wei, Ziming Chen, Jiaqi Ma, Shikui Han, Jianhua Xu, Hang Chang, Xiaojun Liang, Xiaodan Shenzhen Campus of Sun Yat-sen University Shenzhen China Peng Cheng Laboratory Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China The University of Hong Kong Hong Kong Dataa Robotics company Huawei Noah’s Ark Lab Hong Kong The School of Information Science and Technology University of Science and Technology of China Hefei230026 China Abu Dhabi United Arab Emirates

Vision-and-Language Navigation (VLN), as a crucial research problem of Embodied AI, requires an embodied agent to navigate through complex 3D environments following natural language instructions. Recent research has highlighted the promising capacity of large language models (LLMs) in VLN by improving navigational reasoning accuracy and interpretability. However, their predominant use in an offline manner usually suffers from substantial domain gap between the VLN task and the LLM training corpus. This paper proposes a novel strategy called Navigational Chain-of-Thought (NavCoT), where we fulfill parameter-efficient in-domain training to enable self-guided navigational decision, leading to a significant mitigation of the domain gap in a cost-effective manner. Specifically, at each timestep, the LLM is prompted to forecast the navigational chain-of-thought by: 1) acting as a world model to imagine the next observation according to the instruction, 2) selecting the candidate observation that best aligns with the imagination, and 3) determining the action based on the reasoning from the prior steps. In this way, the action prediction can be effectively simplified benefiting from the disentangled reasoning. Through constructing formalized labels for training, the LLM can learn to generate desired and reasonable chain-of-thought outputs for improving the action decision. Experimental results across various training settings and popular VLN benchmarks (e.g., Room-to-Room (R2R), Room-across-Room (RxR), Room-for-Room (R4R)) show the significant superiority of NavCoT over the direct action prediction variants. Through simple parameter-efficient finetuning, our NavCoT outperforms a recent GPT4-based approach with ∼7% relative improvement on the R2R dataset. We believe that NavCoT will help unlock more task-adaptive and scalable LLM-based embodied agents, which are helpful for developing real-world robotics applications. Code is available at https://***/expectorlin/NavC

关键词： Robots

NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning

学校读者我要写书评

暂无评论

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5945-5957页

作者： Bingqian Lin Yunshuang Nie Ziming Wei Jiaqi Chen Shikui Ma Jianhua Han Hang Xu Xiaojun Chang Xiaodan Liang Shenzhen Campus Sun Yat-sen University Shenzhen China Shanghai Jiao Tong University Shanghai China University of Hong Kong Pok Fu Lam Hong Kong Dataa Robotics Company Beijing China Huawei Noah's Ark Lab Shanghai China School of Information Science and Technology University of Science and Technology of China Hefei China Department of Computer Vision Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi UAE Peng Cheng Laboratory Shenzhen China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

Vision-and-Language Navigation (VLN), as a crucial research problem of Embodied AI, requires an embodied agent to navigate through complex 3D environments following natural language instructions. Recent research has highlighted the promising capacity of large language models (LLMs) in VLN by improving navigational reasoning accuracy and interpretability. However, their predominant use in an offline manner usually suffers from substantial domain gap between the VLN task and the LLM training corpus. This paper proposes a novel strategy called Nav igational C hain- o f- T hought (NavCoT), where we fulfill parameter-efficient in-domain training to enable self-guided navigational decision, leading to a significant mitigation of the domain gap in a cost-effective manner. Specifically, at each timestep, the LLM is prompted to forecast the navigational chain-of-thought by: 1) acting as a world model to imagine the next observation according to the instruction, 2) selecting the candidate observation that best aligns with the imagination, and 3) determining the action based on the reasoning from the prior steps. In this way, the action prediction can be effectively simplified benefiting from the disentangled reasoning. Through constructing formalized labels for training, the LLM can learn to generate desired and reasonable chain-of-thought outputs for improving the action decision. Experimental results across various training settings and popular VLN benchmarks (e.g., Room-to-Room (R2R), Room-across-Room (RxR), Room-for-Room (R4R)) show the significant superiority of NavCoT over the direct action prediction variants. Through simple parameter-efficient finetuning, our NavCoT outperforms a recent GPT4-based approach with $\sim$ 7% relative improvement on the R2R dataset. We believe that NavCoT will help unlock more task-adaptive and scalable LLM-based embodied agents, which are helpful for developing real-world robotics applications.

关键词： Navigation Cognition Training Scalability Glass Planning Large language models History Electronic mail Visualization

Wespeaker: A Research and Production Oriented Speaker Embedding Learning Toolkit

学校读者我要写书评

暂无评论

Wespeaker: A Research and Production Oriented Speaker Embedd...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Hongji Wang Chengdong Liang Shuai Wang Zhengyang Chen Binbin Zhang Xu Xiang Yanlei Deng Yanmin Qian CSE Dept MoE Key Lab of AI X-LANCE Lab Shanghai Jiao Tong University Shanghai China Tencent Ethereal Audio Lab Tencent Corporation Shenzhen China WeNet Open Source Community School of Marine Science and Technology Northwestern Polytechnical University Xi’an China NVIDIA Santa Clara USA Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen Horizon Robotics Beijing China AISpeech Ltd Suzhou China

Speaker modeling is essential for many related tasks, such as speaker recognition and speaker diarization. The dominant modeling approach is fixed-dimensional vector representation, i.e., speaker embedding. This paper introduces a research and production oriented speaker embedding learning toolkit, Wespeaker. Wespeaker contains the implementation of scalable data management, state-of-the-art speaker embedding models, loss functions, and scoring back-ends, with highly competitive results achieved by structured recipes which were adopted in the winning systems in several speaker verification challenges. The application to other downstream tasks such as speaker diarization is also exhibited in the related recipe. Moreover, CPU- and GPU-compatible deployment codes are integrated for production-oriented development. The toolkit is publicly available at https://***/wenet-e2e/wespeaker.

关键词： Codes Production Signal processing data models Acoustics Speaker recognition Task analysis

Faster PAC Learning and Smaller Coresets via Smoothed Analysis

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Maalouf, Alaa Tukan, Murad Jubran, Ibrahim Feldman, Dan Robotics and Big Data Lab Department of Computer Science University of Haifa Haifa Israel

PAC-learning usually aims to compute a small subset (Ε-sample/net) from n items, that provably approximates a given loss function for every query (model, classifier, hypothesis) from a given set of queries, up to an additive error Ε ∈ (0, 1). Coresets generalize this idea to support multiplicative error 1 ± Ε. Inspired by smoothed analysis, we suggest a natural generalization: approximate the average (instead of the worst-case) error over the queries, in the hope of getting smaller subsets. The dependency between errors of different queries implies that we may no longer apply the Chernoff-Hoeffding inequality for a fixed query, and then use the VC-dimension or union bound. This paper provides deterministic and randomized algorithms for computing such coresets and Ε-samples of size independent of n, for any finite set of queries and loss function. Example applications include new and improved coreset constructions for e.g. streaming vector summarization [ICML’17] and k-PCA [NIPS’16]. Experimental results with open source code are provided. Copyright © 2020, The Authors. All rights reserved.

关键词： Errors

Coresets for Near-Convex Functions

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Tukan, Murad Maalouf, Alaa Feldman, Dan Robotics and Big Data Lab Department of Computer Science University of Haifa Haifa Israel

Coreset is usually a small weighted subset of n input points in Rd, that provably approximates their loss function for a given set of queries (models, classifiers, etc.). Coresets become increasingly common in machine learning since existing heuristics or inefficient algorithms may be improved by running them possibly many times on the small coreset that can be maintained for streaming distributed data. Coresets can be obtained by sensitivity (importance) sampling, where its size is proportional to the total sum of sensitivities. Unfortunately, computing the sensitivity of each point is problem dependent and may be harder to compute than the original optimization problem at hand. We suggest a generic framework for computing sensitivities (and thus coresets) for wide family of loss functions which we call near-convex functions. This is by suggesting the f-SVD factorization that generalizes the SVD factorization of matrices to functions. Example applications include coresets that are either new or significantly improves previous results, such as SVM, Logistic regression, M-estimators, and `z-regression. Experimental results and open source are also provided. Copyright © 2020, The Authors. All rights reserved.

关键词： Functions

Coresets for near-convex functions 20

学校读者我要写书评

暂无评论

Coresets for near-convex functions

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Murad Tukan Alaa Maalouf Dan Feldman The Robotics and Big Data Lab Department of Computer Science University of Haifa Haifa Israel

ISBN: (纸本)9781713829546

Coreset is usually a small weighted subset of n input points in ℝd, that provably approximates their loss function for a given set of queries (models, classifiers, etc.). Coresets become increasingly common in machine learning since existing heuristics or inefficient algorithms may be improved by running them possibly many times on the small coreset that can be maintained for streaming distributed data. Coresets can be obtained by sensitivity (importance) sampling, where its size is proportional to the total sum of sensitivities. Unfortunately, computing the sensitivity of each point is problem dependent and may be harder to compute than the original optimization problem at hand. We suggest a generic framework for computing sensitivities (and thus coresets) for wide family of loss functions which we call near-convex functions. This is by suggesting the ƒ-SVD factorization that generalizes the SVD factorization of matrices to functions. Example applications include coresets that are either new or significantly improves previous results, such as SVM, Logistic regression, M-estimators, and ℓz-regression. Experimental results and open source are also provided.

关键词：

Adaptive Context Selection for Polyp Segmentation 23rd

学校读者我要写书评

暂无评论

Adaptive Context Selection for Polyp Segmentation

23rd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2020

作者： Zhang, Ruifei Li, Guanbin Li, Zhen Cui, Shuguang Qian, Dahong Yu, Yizhou School of Data and Computer Science Sun Yat-sen University Guangzhou China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong ShenzhenGuangdong China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Deepwise AI Lab Beijing China

ISBN: (纸本)9783030597245

Accurate polyp segmentation is of great significance for the diagnosis and treatment of colorectal cancer. However, it has always been very challenging due to the diverse shape and size of polyp. In recent years, state-of-the-art methods have achieved significant breakthroughs in this task with the help of deep convolutional neural networks. However, few algorithms explicitly consider the impact of the size and shape of the polyp and the complex spatial context on the segmentation performance, which results in the algorithms still being powerless for complex samples. In fact, segmentation of polyps of different sizes relies on different local and global contextual information for regional contrast reasoning. To tackle these issues, we propose an adaptive context selection based encoder-decoder framework which is composed of Local Context Attention (LCA) module, Global Context Module (GCM) and Adaptive Selection Module (ASM). Specifically, LCA modules deliver local context features from encoder layers to decoder layers, enhancing the attention to the hard region which is determined by the prediction map of previous layer. GCM aims to further explore the global context features and send to the decoder layers. ASM is used for adaptive selection and aggregation of context features through channel-wise attention. Our proposed approach is evaluated on the EndoScene and Kvasir-SEG datasets, and shows outstanding performance compared with other state-of-the-art methods. The code is available at https://***/ReaFly/ACSNet. © 2020, Springer Nature Switzerland AG.

关键词： Diagnosis