检索结果-内蒙古大学图书馆

GSLB: The Graph Structure learning Benchmark

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Zhixun Wang, Liang Sun, Xin Luo, Yifan Zhu, Yanqiao Chen, Dingshuo Luo, Yingtao Zhou, Xiangxin Liu, Qiang Wu, Shu Yu, Jeffrey Xu Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Center for Research on Intelligent Perception Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Department of Automation University of Science and Technology of China China School of Cyberspace Security Beijing University of Posts and Telecommunications China Department of Computer Science University of California Los Angeles United States Heinz College of Information Systems and Public Policy Machine Learning Department School of Computer Science Carnegie Mellon University United States

Graph Structure learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB. © 2023, CC BY.

关键词： Benchmarking

CogTree: Cognition tree loss for unbiased scene graph generation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yu, Jing Chai, Yuan Wang, Yujing Hu, Yue Wu, Qi Institute of Information Engineering Chinese Academy of Sciences Beijing China Intelligent Computing and Machine Learning Lab School of ASEE Beihang University Beijing China Key Laboratory of Machine Perception MOE School of EECS Peking University Beijing China University of Adelaide Australia

Scene graphs are semantic abstraction of images that encourage visual understanding and reasoning. However, the performance of Scene Graph Generation (SGG) is unsatisfactory when faced with biased data in real-world scenarios. Conventional debiasing research mainly studies from the view of balancing data distribution or learning unbiased models and representations, ignoring the correlations among the biased classes. In this work, we analyze this problem from a novel cognition perspective: automatically building a hierarchical cognitive structure from the biased predictions and navigating that hierarchy to locate the relationships, making the tail relationships receive more attention in a coarse-to-fine mode. To this end, we propose a novel debiasing Cognition Tree (CogTree) loss for unbiased SGG. We first build a cognitive structure CogTree to organize the relationships based on the prediction of a biased SGG model. The CogTree distinguishes remarkably different relationships at first and then focuses on a small portion of easily confused ones. Then, we propose a debiasing loss specially for this cognitive structure, which supports coarse-to-fine distinction for the correct relationships. The loss is model-agnostic and consistently boosting the performance of several state-of-the-art models. The code is available at: https://***/CYVincent/Scene-Graph-Transformer-CogTree. Copyright © 2020, The Authors. All rights reserved.

关键词： Forestry

Overview of the Tenth Dialog System Technology Challenge: DSTC10

学校读者我要写书评

暂无评论

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 32卷 765-778页

作者： Yoshino, Koichiro Chen, Yun-Nung Crook, Paul Kottur, Satwik Li, Jinchao Hedayatnia, Behnam Moon, Seungwhan Fei, Zhengcong Li, Zekang Zhang, Jinchao Feng, Yang Zhou, Jie Kim, Seokhwan Liu, Yang Jin, Di Papangelis, Alexandros Gopalakrishnan, Karthik Hakkani-Tur, Dilek Damavandi, Babak Geramifard, Alborz Hori, Chiori Shah, Ankit Zhang, Chen Li, Haizhou Sedoc, Joao D'haro, Luis F. Banchs, Rafael Rudnicky, Alexander Guardian Robot Project R-IH RIKEN 2-2-2 Hikaridai Seika Shoraku619-0288 Japan Information Science Nara Institute of Science and Technology Ikoma630-0101 Japan Computer Science and Information Engineering National Taiwan University Taipei10617 Taiwan Inc. Palo AltoCA95054 United States Alexa AI *** Inc. SunnyvaleCA94089 United States Meta Seattle RedmondWA98052 United States Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Tencent AI Lab Beijing Beijing China Kexueyuan South Road Zhongguancun Beijing100190 China Beijing 100190 China Alexa AI *** Inc. SunnyvaleCA United States 1120 Enterprise way Sunnyvale94089 United States *** Inc. SeattleWA United States Menlo Park CA United States Audio and Speech Group Mitsubishi Electric Research Laboratories CambridgeMA02139-1955 United States Carnegie Mellon University Department of Language and Information Technologies or just Carnegie Mellon University Pittsburgh United States National University of Singapore Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Shenzhen Research Institute of Big Data School of Data Science Chinese University of Hong Kong Shenzhen518172 China New York University New YorkNY United States ETSI de Telecomunicacion - Speech Technology and Machine Learning Group Universidad Politecnica de Madrid Ciudad Universitaria Madrid28040 Spain Nanyang Technological University Singapore Singapore Carnegie Mellon University PittsburghPA United States

This article introduces the Tenth Dialog System Technology Challenge (DSTC-10). This edition of the DSTC focuses on applying end-to-end dialog technologies for five distinct tasks in dialog systems, namely 1. Incorporation of Meme images into open domain dialogs, 2. Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations, 3. Situated Interactive Multimodal dialogs, 4. Reasoning for Audio Visual Scene-Aware Dialog, and 5. Automatic Evaluation and Moderation of Open-domainDialogue Systems. This article describes the task definition, provided datasets, baselines, and evaluation setup for each track. We also summarize the results of the submitted systems to highlight the general trends of the state-of-the-art technologies for the tasks. © 2023 The Authors.

关键词： Job analysis

Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Qizhou Han, Bo Liu, Tongliang Niu, Gang Yang, Jian Gong, Chen Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of MoE School of Computer Science and Engineering Nanjing University of Science and Technology China Department of Computer Science Hong Kong Baptist University Hong Kong Trustworthy Machine Learning Lab School of Computer Science Faculty of Engineering The University of Sydney Australia Japan Department of Computing Hong Kong Polytechnic University Hong Kong

The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Deep Neural Networks (DNNs). Existing learning methods with label noise either employ ad-hoc heuristics or restrict to specific noise assumptions. However, more general situations, such as instance-dependent label noise, have not been fully explored, as scarce studies focus on their label corruption process. By categorizing instances into confusing and unconfusing instances, this paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances. The resultant model can be realized by DNNs, where the training procedure is accomplished by employing an alternating optimization algorithm. Experiments on datasets with both synthetic and real-world label noise verify that the proposed method yields significant improvements on robustness over state-of-the-art counterparts. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

Performance Optimization of Wildlife Recognition with Distributed learning in Ecological Surveillance

学校读者我要写书评

暂无评论

Performance Optimization of Wildlife Recognition with Distri...

IEEE International Conference on Cyber Technology in Automation, Control, and intelligent Systems

作者： Wan Dai Hongpeng Wang Yulin Song Yunwei Xin Tianjin Key Laboratory of Intelligent Robotics Tianjin Research Laboratory of Machine Learning and Pervasive Computing Nankai University Tianjin

ISBN: (数字)9781728107707

ISBN: (纸本)9781728107714

Recently, deep learning technology has been widely used in ecological environment monitoring, but there are still huge challenges in specific tasks. For example, data sets have increased over the past few years, and in a CPU environment, training is quite time consuming. In order to solve these problems, we bring up a novel and effective method to improve training speed. In this paper, we make use of multi-GPUs to achieve distributed parallel acceleration. Small and shallow networks are not suitable for distributed training, because the computation of each parameter in this network is much higher than that of multi-layer perception or automatic encoder architecture, we use convolutional neural network with parameter sharing as the training network. In this paper, the main adopted method is to compare the performance of training wildlife recognition in single GPU and multi-GPUs environments by using distributed deep learning framework TensorFlow. The experimental results show that multi-GPUs which adopt distributed architecture can significantly accelerate training time consumption than single GPU. The results of this experiment also provides strong support for our follow-up work.

关键词： Training Parallel processing Graphics processing units Distributed databases Computational modeling Data models Neural networks

learning with Group Noise

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Qizhou Yao, Jiangchao Gong, Chen Liu, Tongliang Gong, Mingming Yang, Hongxia Han, Bo Department of Computer Science Hong Kong Baptist University Hong Kong Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of MoE School of Computer Science and Engineering Nanjing University of Science and Technology China Data Analytics and Intelligence Lab Alibaba Group China Department of Computing Hong Kong Polytechnic University Hong Kong Trustworthy Machine Learning Lab School of Computer Science University of Sydney Australia School of Mathematics and Statistics University of Melbourne Australia

machine learning in the context of noise is a challenging but practical setting to plenty of real-world applications. Most of the previous approaches in this area focus on the pairwise relation (casual or correlational relationship) with noise, such as learning with noisy labels. However, the group noise, which is parasitic on the coarse-grained accurate relation with the fine-grained uncertainty, is also universal and has not been well investigated. The challenge under this setting is how to discover true pairwise connections concealed by the group relation with its fine-grained noise. To overcome this issue, we propose a novel Max-Matching method for learning with group noise. Specifically, it utilizes a matching mechanism to evaluate the relation confidence of each object (cf. Figure 1) w.r.t. the target, meanwhile considering the Non-IID characteristics among objects in the group. Only the most confident object is considered to learn the model, so that the fine-grained noise is mostly dropped. The performance on a range of real-world datasets in the area of several learning paradigms demonstrates the effectiveness of Max-Matching. Copyright © 2021, The Authors. All rights reserved.

关键词： machine learning

Random Occlusion Recovery with Noise Channel for Person Re-identification 16th

学校读者我要写书评

暂无评论

Random Occlusion Recovery with Noise Channel for Person Re-i...

16th International Conference on intelligent computing, ICIC 2020

作者： Zhang, Kun Wu, Di Yuan, Changan Qin, Xiao Wu, Hongjie Zhao, Xingming Zhang, Lijun Du, Yuchuan Wang, Hanli Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Tongji University Shanghai China Guangxi Academy of Science Nanning530025 China School of Computer and Information Engineering Nanning Normal University Nanning530299 China School of Computer Science and Technology Soochow University Suzhou215006 China School of Electronic and Information Engineering Suzhou University of Science and Technology Suzhou215009 China Fudan University Shanghai200433 China Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Ministry of Education Shanghai China Collaborative Innovation Center of Intelligent New Energy Vehicle and School of Automotive Studies Tongji University Shanghai201804 China The Key Laboratory of Road and Traffic Engineering of the Ministry of Education Department of Transportation Engineering Tongji University Shanghai201804 China Department of Computer Science and Technology the Key Laboratory of Embedded System and Service Computing and Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai200092 China

ISBN: (纸本)9783030607982

Person re-identification, as the basic task of a multi-camera surveillance system, plays an important role in a variety of surveillance applications. However, the current mainstream person re-identification model based on deep learning requires a lot of labeled data, which takes a lot of time and manpower. In this study, we proposed a person re-identification method based on random occlusion recovery with noise channel. We add random occlusion blocks to the original image, use the GAN model for repair, and use the repaired image to expand the original training set. After that, the generated image is adjusted through the noise channel. Finally, we use the enhanced data set to train the baseline model. Our model achieves the state-of-the-art on Market-1501 dataset, proving that the method is effective. © 2020, Springer Nature Switzerland AG.

关键词： Generative adversarial networks

Plant Leaf Recognition Based on Conditional Generative Adversarial Nets 15th

学校读者我要写书评

暂无评论

Plant Leaf Recognition Based on Conditional Generative Adver...

15th International Conference on intelligent computing, ICIC 2019

作者： Jiao, Zhihao Zhang, Lijun Yuan, Chang-An Qin, Xiao Shang, Li Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Tongji University Shanghai China Collaborative Innovation Center of Intelligent New Energy Vehicle Shanghai China School of Automotive Studies Tongji University Shanghai China Science Computing and Intelligent Information Processing of GuangXi Higher Education Key Laboratory Nanning Normal University NanningGuangxi China Department of Communication Technology College of Electronic Information Engineering Suzhou Vocational University SuzhouJiangsu215104 China

ISBN: (纸本)9783030267629

Plants play an important role in human life, Identifying and protecting plants has far-reaching implications for the sustainable development of the ecological environment. Plant leaves can often reflect important characteristics of plants, so it is scientific and feasible to effectively identify plant species through plant leaves. With the rapid development of deep learning in recent years, it has been widely applied in plant leaf recognition. Compared with the traditional method, deep learning based plant leaf recognition algorithm can extract plant leaf features more effectively and can greatly improve the performance. Based on the detailed analysis of the structural characteristics of three classical convolutional neural network models, this paper comprehensively compares the recognition performance of three convolutional neural network models on ICL plant leaf datasets. The experimental results show that the Conditional Generative Adversarial Net with optimized output layer has better recognition results on the plant leaf dataset than other convolutional neural network models. © 2019, Springer Nature Switzerland AG.

关键词： Neural network models

Leaf Recognition Based on Capsule Network 15th

学校读者我要写书评

暂无评论

Leaf Recognition Based on Capsule Network

15th International Conference on intelligent computing, ICIC 2019

作者： Zheng, Yang Yuan, Chang-An Shang, Li Huang, Zhi-Kai Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Tongji University Shanghai China Science Computing and Intelligent Information Processing of GuangXi Higher Education Key Laboratory Nanning Normal University NanningGuangxi China Department of Communication Technology College of Electronic Information Engineering Suzhou Vocational University SuzhouJiangsu215104 China College of Mechanical and Electrical Engineering Nanchang Institute of Technology NanchangJiangxi330099 China

ISBN: (纸本)9783030267629

Plant is an indispensable part of human life, so it is very important to identify and protect plants. Convolutional neural network is a commonly used neural network for image recognition. However, convolutional neural network has huge defects. In order to avoid the defects of convolutional neural network, this paper adopts a new type of neural network: capsule neural network to complete plant leaf recognition. The experiment shows that the capsule neural network has a more effective recognition rate than the common neural network in plant leaf recognition. © 2019, Springer Nature Switzerland AG.

关键词： Convolution