检索结果-内蒙古大学图书馆

A Survey of label-Efficient Deep Learning for 3D Point Clouds

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xiao, Aoran Zhang, Xiaoqin Shao, Ling Lu, Shijian School of Computer Science and Engineering Nanyang Technological University Singapore Key Laboratory of Intelligent Informatics for Safety & Emergency of Zhejiang Province Wenzhou University China The UCAS-Terminus AI Lab University of Chinese Academy of Sciences Beijing China

In the past decade, deep neural networks have achieved significant progress in point cloud learning. However, collecting large-scale precisely-annotated point clouds is extremely laborious and expensive, which hinders the scalability of existing point cloud datasets and poses a bottleneck for efficient exploration of point cloud data in various tasks and applications. label-efficient learning offers a promising solution by enabling effective deep network training with much-reduced annotation efforts. This paper presents the first comprehensive survey of label-efficient learning of point clouds. We address three critical questions in this emerging research field: i) the importance and urgency of label-efficient learning in point cloud processing, ii) the subfields it encompasses, and iii) the progress achieved in this area. To this end, we propose a taxonomy that organizes label-efficient learning methods based on the data prerequisites provided by different types of labels. We categorize four typical label-efficient learning approaches that significantly reduce point cloud annotation efforts: data augmentation, domain transfer learning, weakly-supervised learning, and pretrained foundation models. For each approach, we outline the problem setup and provide an extensive literature review that showcases relevant progress and challenges. Finally, we share our views on the current research challenges and potential future directions. A project associated with this survey has been built at https://***/xiaoaoran/3D_label_efficient_learning. © 2023, CC BY-NC-ND.

关键词： Large datasets

CUE: An Uncertainty Interpretation Framework for Text Classifiers Built on Pre-Trained Language Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Jiazheng Sun, Zhaoyue Liang, Bin Gui, Lin He, Yulan Department of Informatics King’s College London United Kingdom Department of Computer Science University of Warwick United Kingdom Joint Lab of HITSZ-CMS Harbin Institute of Technology Shenzhen China The Alan Turing Institute United Kingdom

Text classifiers built on Pre-trained Language Models (PLMs) have achieved remarkable progress in various tasks including sentiment analysis, natural language inference, and question-answering. However, the occurrence of uncertain predictions by these classifiers poses a challenge to their reliability when deployed in practical applications. Much effort has been devoted to designing various probes in order to understand what PLMs capture. But few studies have delved into factors influencing PLM-based classifiers’ predictive uncertainty. In this paper, we propose a novel framework, called CUE, which aims to interpret uncertainties inherent in the predictions of PLM-based models. In particular, we first map PLM-encoded representations to a latent space via a variational auto-encoder. We then generate text representations by perturbing the latent space which causes fluctuation in predictive uncertainty. By comparing the difference in predictive uncertainty between the perturbed and the original text representations, we are able to identify the latent dimensions responsible for uncertainty and subsequently trace back to the input features that contribute to such uncertainty. Our extensive experiments on four benchmark datasets encompassing linguistic acceptability classification, emotion classification, and natural language inference show the feasibility of our proposed framework. Our source code is available at https://***/lijiazheng99/CUE. © 2023, CC BY.

关键词： Sentiment analysis

Knowledge-aware Zero-shot learning: Survey and perspective

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Jiaoyan Geng, Yuxia Chen, Zhuo Horrocks, Ian Pan, Jeff Z. Chen, Huajun Department of Computer Science University of Oxford College of Computer Science AZFT Knowledge Engine Lab Zhejiang University School of Informatics The University of Edinburgh

Zero-shot learning (ZSL) which aims at predicting classes that have never appeared during the training using external knowledge (a.k.a. side information) has been widely investigated. In this paper we present a literature review towards ZSL in the perspective of external knowledge, where we categorize the external knowledge, review their methods and compare different external knowledge. With the literature review, we further discuss and outlook the role of symbolic knowledge in addressing ZSL and other machine learning sample shortage issues. Copyright © 2021, The Authors. All rights reserved.

关键词：

Policy learning from tutorial books via understanding, rehearsing and introspecting 24

学校读者我要写书评

暂无评论

Policy learning from tutorial books via understanding, rehea...

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Xiong-Hui Chen Ziyan Wang Yali Du Shengyi Jiang Meng Fang Yang Yu Jun Wang National Key Laboratory for Novel Software Technology Nanjing University China & School of Artificial Intelligence Nanjing University China Cooperative AI Lab Department of Informatics King's College London The University of Hong Kong University of Liverpool AI Centre Department of Computer Science University College London

ISBN: (纸本)9798331314385

When humans need to learn a new skill, we can acquire knowledge through written books, including textbooks, tutorials, etc. However, current research for decisionmaking, like reinforcement learning (RL), has primarily required numerous real interactions with the target environment to learn a skill, while failing to utilize the existing knowledge already summarized in the text. The success of Large Language Models (LLMs) sheds light on utilizing such knowledge behind the books. In this paper, we discuss a new policy learning problem called Policy Learning from tutorial Books (PLfB) upon the shoulders of LLMs' systems, which aims to leverage rich resources such as tutorial books to derive a policy network. Inspired by how humans learn from books, we solve the problem via a three-stage framework: Understanding, Rehearsing, and Introspecting (URI). In particular, it first rehearses decision-making trajectories based on the derived knowledge after understanding the books, then introspects about the imaginary dataset to distill a policy network. We build two benchmarks for PLfB based on Tic-Tac-Toe and Football games. In the experiment, URI's policy achieves a minimum of 44% net winning rate against GPT-based agents without any real data. In the much more complex football game, URI's policy beat the built-in AIs with a 37% winning rate while GPT-based agents can only achieve a 6% winning rate. The project page: https://***/.

关键词：

Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Runfa Rong, Yu Guo, Shangmin Han, Jiaqi Sun, Fuchun Xu, Tingyang Huang, Wenbing State Key Lab on Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University China Tsinghua University China Tencent AI lab School of Informatics University of Edinburgh United Kingdom

After the great success of Vision Transformer variants (ViTs) in computer vision, it has also demonstrated great potentials in domain adaptive semantic segmentation. Unfortunately, straightforwardly applying local ViTs in domain adaptive semantic segmentation does not bring in expected improvement. We find that the pitfall of local ViTs is due to the severe high-frequency components generated during both the pseudo-label construction and features alignment for target domains. These high-frequency components make the training of local ViTs very unsmooth and hurts their transferability. In this paper, we introduce a low-pass filtering mechanism, momentum network, to smooth the learning dynamics of target domain features and pseudo labels. Furthermore, we propose a dynamic of discrepancy measurement to align the distributions in the source and target domains via dynamic weights to evaluate the importance of the samples. After tackling above issues, extensive experiments on sim2real benchmarks show that the proposed method outperforms the state-of-the-art methods. Our codes are available at https://***/alpc91/TransDA. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantic Segmentation

TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lou, Meng Zhang, Shu Zhou, Hong-Yu Yang, Sibei Wu, Chuan Yu, Yizhou School of Computing and Data Science The University of Hong Kong Hong Kong AI Lab Deepwise Healthcare Beijing China Department of Biomedical Informatics Harvard Medical School Boston United States Department of Computer Science The University of Hong Kong Hong Kong School of Information Science and Technology ShanghaiTech University Shanghai China

Recent studies have integrated convolutions into transformers to introduce inductive bias and improve generalization performance. However, the static nature of conventional convolution prevents it from dynamically adapting to input variations, resulting in a representation discrepancy between convolution and self-attention as the latter computes attention maps dynamically. Furthermore, when stacking token mixers that consist of convolution and self-attention to form a deep network, the static nature of convolution hinders the fusion of features previously generated by self-attention into convolution kernels. These two limitations result in a sub-optimal representation capacity of the entire network. To find a solution, we propose a lightweight Dual Dynamic Token Mixer (D-Mixer) to simultaneously learn global and local dynamics via computing input-dependent global and local aggregation weights. D-Mixer works by applying an efficient global attention module and an input-dependent depthwise convolution separately on evenly split feature segments, endowing the network with strong inductive bias and an enlarged receptive field. We use D-Mixer as the basic building block to design TransXNet, a novel hybrid CNN-Transformer vision backbone network that delivers compelling performance. In the ImageNet-1K classification, TransXNet-T surpasses Swin-T by 0.3% in top-1 accuracy while requiring less than half of the computational cost. Furthermore, TransXNet-S and TransXNet-B exhibit excellent model scalability, achieving top-1 accuracy of 83.8% and 84.6% respectively, with reasonable computational costs. Additionally, our proposed network architecture demonstrates strong generalization capabilities in various dense prediction tasks, outperforming other state-of-the-art networks while having lower computational costs. Code is publicly available at https://***/LMMMEng/TransXNet. © 2023, CC BY.

关键词： Mixers (machinery)

GNN2R: Weakly-Supervised Rationale-Providing Question Answering over Knowledge Graphs

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Ruijie Rossetto, Luca Cochez, Michael Bernstein, Abraham The Department of Informatics University of Zurich Zurich Switzerland The University Research Priority Program "Dynamics of Healthy Aging" University of Zurich Zurich Switzerland The Department of Computer Science Vrije Universiteit Amsterdam Amsterdam Netherlands Discovery Lab Elsevier Amsterdam Netherlands

Most current methods for multi-hop question answering (QA) over knowledge graphs (KGs) only provide final conclusive answers without explanations, such as a set of KG entities that is difficult for normal users to review and comprehend. This issue severely limits the application of KG-based QA in real-world scenarios. However, it is non-trivial to solve due to two challenges: First, annotations of reasoning chains of multi-hop questions, which could serve as supervision for explanation generation, are usually lacking. Second, it is difficult to maintain high efficiency when explicit KG triples need to be retrieved to generate explanations. In this paper, we propose a novel Graph Neural Network-based Two-Step Reasoning model (GNN2R) to solve this issue. GNN2R can provide both final answers and reasoning subgraphs as a rationale behind final answers efficiently with only weak supervision that is available through question-final answer pairs. We extensively evaluated GNN2R with detailed analyses in experiments. The results demonstrate that, in terms of effectiveness, efficiency, and quality of generated explanations, GNN2R outperforms existing state-of-the-art methods that are applicable to this task. Our code and pre-trained models are available at https://***/ruijie-wang-uzh/GNN2R. Copyright © 2023, The Authors. All rights reserved.

关键词： Knowledge graph

Effective Searching for the Honeybee Queen in a Living Colony

学校读者我要写书评

暂无评论

Effective Searching for the Honeybee Queen in a Living Colon...

IEEE International Conference on Automation science and Engineering (CASE)

作者： Jan Blaha Jan Mikula Tomáš Vintr Jiří Janota Jiří Ulrich Tomáš Rouček Fatemeh Rekabi-Bana Laurenz Alexander Fedotoff Martin Stefanec Thomas Schmickl Farshad Arvin Miroslav Kulich Tomáš Krajník Faculty of Electrical Engineering Czech Technical University in Prague Czechia Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Czechia Computer Science Department Durham University United Kingdom Department of Zoology Artificial Life Lab Institute of Biology University of Graz Graz Austria

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Despite the importance of honeybees as pollinators for the entire ecosystem and their recent decline threatening agricultural production, the dynamics of the living colony are not well understood. In our EU H2020 RoboRoyale project, we aim to support the pollination activity of the honeybees through robots interacting with the core element of the honeybee colony, the honeybee queen. In order to achieve that, we need to understand how the honeybee queen behaves and interacts with the surrounding worker bees. To gather the necessary data, we observe the queen with a moving camera, and occasionally, we instruct the system to perform selective observations elsewhere. In this paper, we deal with the problem of searching for the honeybee queen inside a living colony. We demonstrate that combining spatio-temporal models of queen presence with efficient search methods significantly decreases the time required to find her. This will minimize the chance of missing interesting data on the infrequent behaviors or queen-worker interactions, leading to a better understanding of the queen’s behavior over time. Moreover, a faster search for the queen allows the robot to leave her more frequently and gather more data in other areas of the honeybee colony.

关键词： computer aided software engineering Automation Biological system modeling Ecosystems Robot vision systems Production Search problems Cameras Path planning Robots

Optg: Optimizing Gradient-Driven Criteria in Network Sparsity

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Zhang, Yuxin Lin, Mingbao Chen, Mengzhao Chao, Fei Tian, Yonghong Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China Tecent Youtu Lab China Department of Computer Science and Technology Peking University China Peng Cheng Laboratory China Department of Artificial Intelligence School of Informatics Xiamen University China

Network sparsity receives popularity mostly due to its capability to reduce the complexity of the network. Extensive studies excavate gradient-driven sparsity. Typically, these methods are constructed upon the premise of weight independence, which however, is contrary to the fact that weights are mutually influenced. Thus, their performance remains to be improved. In this paper, we propose to optimize gradient-driven sparsity (OptG) by solving this independence paradox. Our motive comes from the recent advances in supermask training which shows that high-performing sparse subnetworks can be located by simply updating mask values without modifying any weight. We prove that supermask training is to accumulate the criteria of gradientdriven sparsity for both removed and preserved weights, and it can partly solve the independence paradox. Consequently, OptG integrates supermask training into gradient-driven sparsity, and a novel supermask optimizer is further proposed to comprehensively mitigate the independence paradox. Experiments show that OptG can well surpass many existing state-of-the-art competitors, especially at ultra-high sparsity levels. Our project is available at \url{https://***/zyxxmu/OptG}. © 2024, The Authors. All rights reserved.

关键词： Image classification