检索结果-内蒙古大学图书馆

Augmentation-based discriminative meta-learning for cross-machine few-shot fault diagnosis

学校读者我要写书评

暂无评论

science China(Technological sciences) 2023年第6期66卷 1698-1716页

作者： XIA PengCheng HUANG YiXiang WANG YuXiang LIU ChengLiang LIU Jie State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong UniversityShanghai 200240China MoE Key Lab of Artificial Intelligence AI InstituteShanghai Jiao Tong UniversityShanghai 200240China Department of Mechanical and Aerospace Engineering Carleton UniversityOttawa ON K1S 5B6Canada

Deep learning methods have demonstrated promising performance in fault diagnosis *** the scarcity of data in industrial scenarios limits the practical application of such methods,transfer learning effectively tackles this issue through crossmachine knowledge ***,the cross-machine few-shot problem,which is a more general industrial scenario,has been rarely *** studies have not considered the cross-machine domain shift problem,which results in poor testing *** paper proposes an augmentation-based discriminative meta-learning method to address this *** the meta-training process,signal transformation is proposed to increase the meta-task diversity for more robust feature learning,and multi-scale learning is combined for more adaptive feature *** the meta-testing process,limited labeled fault information is used to promote model generalization in the target domain through quasi-meta-training based on data ***,a novel hyperbolic prototypical loss is proposed for more discriminative feature representation and separable category prototypes by designing a hyperbolic decision ***-machine few-shot diagnosis experiments were conducted using three datasets from different machines,namely,the bearing,motor,and gear *** effectiveness of the proposed method was verified through ablation and comparison studies.

关键词： fault diagnosis few-shot learning meta-learning data augmentation cross-machine discriminative loss

Corruption Robust Dynamic Pricing in Liner Shipping under Capacity Constraint

学校读者我要写书评

暂无评论

Corruption Robust Dynamic Pricing in Liner Shipping under Ca...

International Conference on Data engineering

作者： Yongyi Hu Xueyan Lit Xikai Wei Yangguang Shi Xiaofeng Gao Guihai Chen Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China School of Computer Science and Technology Shandong University China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

The shipping industry has irreplaceable importance in international trade and commerce. How to dynamically price different containers has long been a hot topic due to its direct connection to the final revenue. Two critical observations have been made after a comprehensive survey within a top liner company, China Ocean Shipping Company (COSCO). (1) Each type of container carried on a liner ship has its maximum capacity. (2) The sales volume is occasionally subject to huge fluctuations due to rare uncontrollable factors, such as COVID. Based on the above two points and the liner routine's periodic nature, we model the dynamic pricing problem as an episodic MDP model integrating with both capacity constraints and adversarial corruption, named C3-MDP. To maximize the cumulative revenue in the C3-MDP setting, we propose a programming framework, Bonus-Exploration based Episodic Programming (BEEP). This framework can directly accommodate the linear programming algorithm to form the algorithm BEEP-LP, which provides the episode-wise greedy optimal strategy. Furthermore, a detailed regret analysis is provided, showing that BEEP-LP has a regret that is sublinear in the number of episodes. Combining deep techniques, we also present an approximation algorithm BEEP-DQN in the case of large state-action space to strike a balance between the running time and the performance. Abundant experiments based on real container sales data exhibit the rationality of C3-MDP and the effectiveness of BEEP.

关键词： Industries Surveys Pandemics Heuristic algorithms Oceans Pricing Companies

A Compact Large-Scale Wideband Dual-Polarized Decoupled Patch Antenna Array for Integrated Sensing and Communication 11

学校读者我要写书评

暂无评论

A Compact Large-Scale Wideband Dual-Polarized Decoupled Patc...

11th IEEE Asia-Pacific Conference on Antennas and Propagation, APCAP 2023 - Proceedings

作者： Ma, Lina Shao, Zijian Gu, Changzhan Mao, Junfa China Shanghai Jiao Tong University MoE Key Laboratory of Artificial Intelligence Shanghai China Princeton University Department of Electrical and Computer Engineering PrincetonNJ United States

ISBN: (纸本)9798350326277

In this paper, a compact large-scale wideband large-scale dual-linearly polarized patch antenna array is proposed for integrated sensing and communication (ISAC) at the ISM band. The decoupling technique is applied for a 2 ×42-D antenna array under the extremely close edge-to-edge distance of 1 mm (0.019 λ0). A prototype of this wideband decoupled 2-D patch antenna array is simulated, fabricated, and measured to validate the feasibility of the proposed method. Both the simulation and measured results show that the poor isolations have improved to better than 13 dB within a wide operating bandwidth of more than 10.6%, and the radiation patterns have been corrected obviously, which indicates the proposed decoupling scheme possesses the promising potential for large-scale antenna array applications for wideband multiple-input and multiple-output (MIMO) systems in ISAC. © 2023 IEEE.

关键词： decoupling dual-polarized integrated sensing and communication (ISAC) multiple-input and multiple-output (MIMO) patch antenna wideband

Deep Image Harmonization with Learnable Augmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Niu, Li Cao, Junyan Cong, Wenyan Zhang, Liqing Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China

The goal of image harmonization is adjusting the foreground appearance in a composite image to make the whole image harmonious. To construct paired training images, existing datasets adopt different ways to adjust the illumination statistics of foregrounds of real images to produce synthetic composite images. However, different datasets have considerable domain gap and the performances on small-scale datasets are limited by insufficient training data. In this work, we explore learnable augmentation to enrich the illumination diversity of small-scale datasets for better harmonization performance. In particular, our designed SYthetic COmposite Network (SycoNet) takes in a real image with foreground mask and a random vector to learn suitable color transformation, which is applied to the foreground of this real image to produce a synthetic composite image. Comprehensive experiments demonstrate the effectiveness of our proposed learnable augmentation for image harmonization. The code of SycoNet is released at https://***/bcmi/SycoNet-Adaptive-Image-Harmonization. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillation

学校读者我要写书评

暂无评论

Deep Image Harmonization with Globally Guided Feature Transf...

International Conference on computer Vision (ICCV)

作者： Li Niu Linfeng Tan Xinhao Tao Junyan Cao Fengjun Guo Teng Long Liqing Zhang Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University INTSIG

Given a composite image, image harmonization aims to adjust the foreground illumination to be consistent with background. Previous methods have explored transforming foreground features to achieve competitive performance. In this work, we show that using global information to guide foreground feature transformation could achieve significant improvement. Besides, we propose to transfer the foreground-background relation from real images to composite images, which can provide intermediate supervision for the transformed encoder features. Additionally, considering the drawbacks of existing harmonization datasets, we also contribute a ccHarmony dataset which simulates the natural illumination variation. Extensive experiments on iHarmony4 and our contributed dataset demonstrate the superiority of our method. Our ccHarmony dataset is released at https://***/bcmi/Image-HarmonizationDataset-ccHarmony.

关键词：

DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Qingyang Wang, Jianting Niu, Li Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China

Image composition refers to inserting a foreground object into a background image to obtain a composite image. In this work, we focus on generating plausible shadow for the inserted foreground object to make the composite image more realistic. To supplement the existing small-scale dataset DESOBA, we create a large-scale dataset called DESOBAv2 by using object-shadow detection and inpainting techniques. Specifically, we collect a large number of outdoor scene images with object-shadow pairs. Then, we use pretrained inpainting model to inpaint the shadow region, resulting in the deshadowed images. Based on real images and deshadowed images, we can construct pairs of synthetic composite images and ground-truth target images. Dataset is available at https://***/bcmi/Object-Shadow-Generation-Dataset-DESOBAv2. Copyright © 2023, The Authors. All rights reserved.

关键词： Large dataset

Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Yiting Zhou, Zhanpeng Yan, Junchi Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China

The behavior of neural networks still remains opaque, and a recently widely noted phenomenon is that networks often achieve similar performance when initialized with different random parameters. This phenomenon has attracted significant attention in measuring the similarity between features learned by distinct networks. However, feature similarity could be vague in describing the same feature since equivalent features hardly exist. In this paper, we expand the concept of equivalent feature and provide the definition of what we call functionally equivalent features. These features produce equivalent output under certain transformations. Using this definition, we aim to derive a more intrinsic metric for the so-called feature complexity regarding the redundancy of features learned by a neural network at each layer. We offer a formal interpretation of our approach through the lens of category theory, a well-developed area in mathematics. To quantify the feature complexity, we further propose an efficient algorithm named Iterative Feature Merging. Our experimental results validate our ideas and theories from various perspectives. We empirically demonstrate that the functionally equivalence widely exists among different features learned by the same neural network and we could reduce the number of parameters of the network without affecting the performance. We have also drawn several interesting empirical findings, including: 1) the larger the network, the more redundant features it learns;2) in particular, we show how to prune the networks based on our finding using direct equivalent feature merging, without fine-tuning which is often needed in peer network pruning methods;3) same structured networks with higher feature complexity achieve better performance;4) through the layers of a neural network, the feature complexity first increase then decrease;5) for the image classification task, a group of functionally equivalent features may correspond to a specific low-level s

关键词： Merging

Painterly Image Harmonization via Adversarial Residual Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Xudong Niu, Li Cao, Junyan Hong, Yan Zhang, Liqing Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China

Image compositing plays a vital role in photo editing. After inserting a foreground object into another background image, the composite image may look unnatural and inharmonious. When the foreground is photorealistic and the background is an artistic painting, painterly image harmonization aims to transfer the style of background painting to the foreground object, which is a challenging task due to the large domain gap between foreground and background. In this work, we employ adversarial learning to bridge the domain gap between foreground feature map and background feature map. Specifically, we design a dual-encoder generator, in which the residual encoder produces the residual features added to the foreground feature map from main encoder. Then, a pixel-wise discriminator plays against the generator, encouraging the refined foreground feature map to be indistinguishable from background feature map. Extensive experiments demonstrate that our method could achieve more harmonious and visually appealing results than previous methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

DreamCom: Finetuning Text-guided Inpainting Model for Image Composition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lu, Lingxiao Li, Jiangtong Zhang, Bo Niu, Li Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China

The goal of image composition is merging a foreground object into a background image to obtain a realistic composite image. Recently, generative composition methods are built on large pretrained diffusion models, due to their unprecedented image generation ability. However, they are weak in preserving the foreground object details. Inspired by recent text-to-image generation customized for certain object, we propose DreamCom by treating image composition as text-guided image inpainting customized for certain object. Specifically, we finetune pretrained text-guided image inpainting model based on a few reference images containing the same object, during which the text prompt contains a special token associated with this object. Then, given a new background, we can insert this object into the background with the text prompt containing the special token. In practice, the inserted object may be adversely affected by the background, so we propose masked attention mechanisms to avoid negative background interference. Experimental results on DreamEditBench and our contributed MureCom dataset show the outstanding performance of our DreamCom. Copyright © 2023, The Authors. All rights reserved.

关键词： Image processing