检索结果-内蒙古大学图书馆

Deep Learning Methods for Ship Classification: From Visible to Infrared images

学校读者我要写书评

暂无评论

Deep Learning Methods for Ship Classification: From Visible ...

Robotics, Intelligent Control and Artificial Intelligence (RICAI), International Conference on

作者： Tianci Liu Hengjia Qin Zhuo Zhan Yunpeng Liu Chinese Academy of Sciences Shenyang Institute of Automation Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China University of Chinese Academy of Sciences Beijing China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang China Key Laboratory of Image Understanding and Computer Vision Shenyang Liaoning Province China The Third Military Representative Office of the Air Force Equipment Department in Shenyang Region Shenyang Liaoning Province China

Deep learning methods have achieved excellent performances on visual tasks of target recognition and classification. The rapid development of autonomous seafaring vessels comes up with the requirement to recognize other maritime ships day and night. However, the recognition of ships based on the deep neural networks may not always access the results as expectation when the ships are under the nighttime environment. To this issue, we consider the ship recognition task under the deep learning framework with paired visible images and infrared images. In this article, we propose an end-to-end convolutional network based on visible images and infrared images of the autonomous seafaring vessels. To demonstrate the effectiveness of our model, we choose the V AIS dataset to test the performance of classifying the maritime ships. Experimental results show that the proposed network outperforms the state-of-the-art methods based on the V AIS database.

关键词：

Probabilistic margins for instance reweighting in adversarial training 21

学校读者我要写书评

暂无评论

Probabilistic margins for instance reweighting in adversaria...

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Qizhou Wang Feng Liu Bo Han Tongliang Liu Chen Gong Gang Niu Mingyuan Zhou Masashi Sugiyama Department of Computer Science Hong Kong Baptist University DeSI Lab Australian Artificial Intelligence Institute University of Technology Sydney TML Lab School of Computer Science Faculty of Engineering The University of Sydney PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of MoE and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology RIKEN Center for Advanced Intelligence Project (AIP) McCombs School of Business The University of Texas at Austin RIKEN Center for Advanced Intelligence Project (AIP) and Graduate School of Frontier Sciences The University of Tokyo

ISBN: (纸本)9781713845393

Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more critical and given larger weights. However, existing methods measuring the closeness are not very reliable: they are discrete and can take only a few values, and they are path-dependent, i.e., they may change given the same start and end points with different attack paths. In this paper, we propose three types of probabilistic margin (PM), which are continuous and path-independent, for measuring the aforementioned closeness and reweighting adversarial data. Specifically, a PM is defined as the difference between two estimated class-posterior probabilities, e.g., such a probability of the true label minus the probability of the most confusing label given some natural data. Though different PMs capture different geometric properties, all three PMs share a negative correlation with the vulnerability of data: data with larger/smaller PMs are safer/riskier and should have smaller/larger weights. Experiments demonstrated that PMs are reliable and PM-based reweighting methods outperformed state-of-the-art counterparts.

关键词：

Hyperspectral image classification with context-aware dynamic graph convolutional network

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wan, Sheng Gong, Chen Zhong, Ping Pan, Shirui Li, Guangyu Yang, Jian PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China National Key Laboratory of Science and Technology on ATR National University of Defense Technology Changsha410073 China Faculty of Information Technology Monash University ClaytonVIC3800 Australia

In hyperspectral image (HSI) classification, spatial context has demonstrated its significance in achieving promising performance. However, conventional spatial context-based methods simply assume that spatially neighboring pixels should correspond to the same land-cover class, so they often fail to correctly discover the contextual relations among pixels in complex situations, and thus leading to imperfect classification results on some irregular or inhomogeneous regions such as class boundaries. To address this deficiency, we develop a new HSI classification method based on the recently proposed Graph Convolutional Network (GCN), as it can flexibly encode the relations among arbitrarily structured non-Euclidean data. Different from traditional GCN, there are two novel strategies adopted by our method to further exploit the contextual relations for accurate HSI classification. First, since the receptive field of traditional GCN is often limited to fairly small neighborhood, we proposed to capture long range contextual relations in HSI by performing successive graph convolutions on a learned region-induced graph which is transformed from the original 2D image grids. Second, we refine the graph edge weight and the connective relationships among image regions by learning the improved adjacency matrix and the 'edge filter', so that the graph can be gradually refined to adapt to the representations generated by each graph convolutional layer. Such updated graph will in turn result in accurate region representations, and vice versa. The experiments carried out on three real-world benchmark datasets demonstrate that the proposed method yields significant improvement in the classification performance when compared with some state-of-the-art approaches. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label image Classification

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Lei Zhan, Yibing Ma, Leilei Tao, Dapeng Ding, Liang Gong, Chen The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing210094 China The JD Explore Academy Beijing100000 China The School of Computer Science and Technology Anhui University Anhui Heifei230601 China The FIST LAB School of Information Science and Engineering Yunnan University Yunnan Kunming650091 China

Recently, Mix-style data augmentation methods (e.g., Mixup and CutMix) have shown promising performance in various visual tasks. However, these methods are primarily designed for single-label images, ignoring the considerable discrepancies between single- and multi-label images, i.e., a multi-label image involves multiple co-occurred categories and fickle object scales. On the other hand, previous multi-label image classification (MLIC) methods tend to design elaborate models, bringing expensive computation. In this paper, we introduce a simple but effective augmentation strategy for multi-label image classification, namely SpliceMix. The "splice" in our method is two-fold: 1) Each mixed image is a splice of several downsampled images in the form of a grid, where the semantics of images attending to mixing are blended without object deficiencies for alleviating co-occurred bias;2) We splice mixed images and the original mini-batch to form a new SpliceMixed mini-batch, which allows an image with different scales to contribute to training together. Furthermore, such splice in our SpliceMixed mini-batch enables interactions between mixed images and original regular images. We also offer a simple and non-parametric extension based on consistency learning (SpliceMix-CL) to show the flexible extensibility of our SpliceMix. Extensive experiments on various tasks demonstrate that only using SpliceMix with a baseline model (e.g., ResNet) achieves better performance than state-of-the-art methods. Moreover, the generalizability of our SpliceMix is further validated by the improvements in current MLIC methods when married with our SpliceMix. The code is available at https://***/zuiran/SpliceMix. Copyright © 2023, The Authors. All rights reserved.

关键词： image classification

A single-loop accelerated extra-gradient difference algorithm with improved complexity bounds for constrained minimax optimization 23

学校读者我要写书评

暂无评论

A single-loop accelerated extra-gradient difference algorith...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yuanyuan Liu Fanhua Shang Weixin An Junhao Liu Hongying Liu Zhouchen Lin 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 Medical College Tianjin University China and Peng Cheng Laboratory National Key Lab of General AI School of Intelligence Science and Technology Peking University and Institute for Artificial Intelligence Peking University and Peng Cheng Laboratory

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 Õ(ε-4), where Õ(·) hides logarithmic factors compared to Õ(·). As the special cases of the constrained NC-NC setting, the proposed algorithm can also obtain the same complexity Õ(ε-2) for both the nonconvex-concave (NC-C) and convex-nonconcave (C-NC) cases, while the best-known complexity bounds are Õ(ε-2.5) for the NC-C case and Õ(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 Õ(ε-3) to Õ(ε-2). To the best of our knowledge, this is the first time that the proposed algorithm improves the best-known complexity bounds from Õ(ε-4) and Õ(ε-3) to Õ(ε-2) in both the NC-NC and NC-C settings.

关键词：

Diff-Reg: Diffusion Model in Doubly Stochastic Matrix Space for Registration Problem

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Qianliang Jiang, Haobo Luo, Lei Li, Jun Ding, Yaqing Xie, Jin Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Intelligence Science and Technology Nanjing University Suzhou China Visual Recognition Group Faculty of Electrical Engineering Czech Technical University in Prague Prague Czech Republic National University of Singapore Singapore

Establishing reliable correspondences is essential for 3D and 2D-3D registration tasks. Existing methods commonly leverage geometric or semantic point features to generate potential correspondences. However, these features may face challenges such as large deformation, scale inconsistency, and ambiguous matching problems (e.g., symmetry). Additionally, many previous methods, which rely on single-pass prediction, may struggle with local minima in complex scenarios. To mitigate these challenges, we introduce a diffusion matching model for robust correspondence construction. Our approach treats correspondence estimation as a denoising diffusion process within the doubly stochastic matrix space, which gradually denoises (refines) a doubly stochastic matching matrix to the ground-truth one for high-quality correspondence estimation. It involves a forward diffusion process that gradually introduces Gaussian noise into the ground truth matching matrix and a reverse denoising process that iteratively refines the noisy one. In particular, we deploy a lightweight denoising strategy during the inference phase. Specifically, once points/image features are extracted and fixed, we utilize them to conduct multiple-pass denoising predictions in the reverse sampling process. Evaluation of our method on both 3D and 2D-3D registration tasks confirms its effectiveness. The code is available at https://***/wuqianliang/Diff-Reg. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

Improved rice algorithm of lossless compression for on-board images

学校读者我要写书评

暂无评论

Improved rice algorithm of lossless compression for on-board...

International Conference on Multimedia Technology

作者： Wei, Yong-Wang Ding, Qing-Hai Luo, Hai-Bo Shenyang Institute of Automation Chinese Academy of Science Shenyang 110016 China Graduate School of Chinese Academy of Science Beijing 100049 China Key Laboratory of Optical-Electronics Information Processing Chinese Academy of Science Shenyang 110016 China Key Laboratory of Image Understanding and Computer Vision Liaoning Province 110016 China Electrical and Information Engineering College Beihua University Jilin 132021 China Research Institute of General Development and Demonstration of Equipment Equipment Academy of Air Force Beijing100076 China

ISBN: (纸本)9781424478743

Aiming at the problems of the relatively lower compression ratio and the difficulty in hardware implementation regarding Rice lossless compression algorithm for the Space-borne Remote-sensing images, an improved Rice method is proposed in which the length of predictor FIFO is determined by the size of input images and the global unicode for differences is used. The improved Rice algorithm is mainly composed of two steps, MED prediction for the whole row data and Rice global uniform entropy coding. The statistical results show that it can significantly reduce the spatial redundancy of the adjacent pixels and the mean value of image differences. The compression bit rate is reduced approximately 0.4581 bpp(bit/pixel) against the original Rice algorithm. Furthermore, the new way reserves the all detail information of the input images throughout the whole encoding process. Because we split the all samples with the same mode, the proportion of the identifier of the splitting mechanic in the output data stream is reduced and the compression ratio is increased. The improvement can reduce the encoding complexity and be easily implemented for hardware application. ©2010 IEEE.

关键词： Signal encoding

JobFormer: Skill-Aware Job Recommendation with Semantic-Enhanced Transformer

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guan, ZhiHao Yang, Jia-Qi Yang, Yang Zhu, Hengshu Li, Wenjie Xiong, Hui the Nanjing University of Science and Technology Nanjing210094 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China Career Science Lab BOSS Zhipin Beijing100028 China the Hong Kong Polytechnic University Hong Kong the Artificial Intelligence Thrust The Hong Kong University of Science and Technology Guangzhou China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

Job recommendation aims to provide potential talents with suitable job descriptions (JDs) consistent with their career trajectory, which plays an essential role in proactive talent recruitment. In real-world management scenarios, the available JD-user records always consist of JDs, user profiles, and click data, in which the user profiles are typically summarized as the user’s skill distribution for privacy reasons. Although existing sophisticated recommendation methods can be directly employed, effective recommendation still has challenges considering the information deficit of JD itself and the natural heterogeneous gap between JD and user profile. To address these challenges, we proposed a novel skill-aware recommendation model based on the designed semantic-enhanced transformer to parse JDs and complete personalized job recommendation. Specifically, we first model the relative items of each JD and then adopt an encoder with the local-global attention mechanism to better mine the intra-job and inter-job dependencies from JD tuples. Moreover, we adopt a two-stage learning strategy for skill-aware recommendation, in which we utilize the skill distribution to guide JD representation learning in the recall stage, and then combine the user profiles for final prediction in the ranking stage. Consequently, we can embed rich contextual semantic representations for learning JDs, while skill-aware recommendation provides effective JD-user joint representation for click-through rate (CTR) prediction. To validate the superior performance of our method for job recommendation, we present a thorough empirical analysis of large-scale real-world and public datasets to demonstrate its effectiveness and interpretability. Copyright © 2024, The Authors. All rights reserved.

关键词： User profile

Simulation of realistic infrared texture of grassland

学校读者我要写书评

暂无评论

Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument 2011年第12 SUPPL.期32卷 103-108页

作者： Liu, Qian Zhu, Feng Hao, Yingming Shenyang Institute of Automation Chinese Acad. of Sci. Shenyang 110016 China Graduate School of the Chinese Acad. of Sci. Beijing 110080 China Key Laboratory of Opto-Electronics Information Processing Chinese Acad. of Sci. Shenyang 110016 China Key Lab. of Image Understanding and Computer Vision Liaoning Shenyang 110016 China

A new method is introduced to simulate realistic infrared texture of grassland. First, the radiative temperature of grassland is solved by integrating material composition, environmental and meteorological factors. As the spectroscopic properties of grass and soil vary greatly, the infrared radiation characteristics are computed respectively. Next, the texture structure of grassland is modeled based on the analysis of spatial distribution of natural grassland. Finally, the infrared radiance of grass and soil are mapped to image space and a realistic grassland texture is generated. Experiment results show that similar visual features exhibit between simulated textures and actual grassland textures, which justifies the effectiveness of the proposed method.

关键词： Infrared radiation