检索结果-内蒙古大学图书馆

OcTr: Octree-Based Transformer for 3D Object Detection

学校读者我要写书评

暂无评论

OcTr: Octree-Based Transformer for 3D Object Detection

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Chao Zhou Yanan Zhang Jiaxin Chen Di Huang State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

A key challenge for LiDAR-based 3D object detection is to capture sufficient features from large scale 3D scenes especially for distant or/and occluded objects. Albeit recent efforts made by Transformers with the long sequence modeling capability, they fail to properly balance the accuracy and efficiency, suffering from inadequate receptive fields or coarse-grained holistic correlations. In this paper, we propose an Octree-based Transformer, named OcTr, to address this issue. It first constructs a dynamic octree on the hierarchical feature pyramid through conducting self-attention on the top level and then recursively propagates to the level below restricted by the octants, which captures rich global context in a coarse-to-fine manner while maintaining the computational complexity under control. Furthermore, for enhanced foreground perception, we propose a hybrid positional embedding, composed of the semantic-aware positional embedding and attention mask, to fully exploit semantic and geometry clues. Extensive experiments are conducted on the Waymo Open Dataset and KITTI Dataset, and OcTr reaches newly state-of-the-art results.

关键词：

A Survey of Source Code Search: A 3-Dimensional Perspective

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sun, Weisong Fang, Chunrong Ge, Yifei Hu, Yuling Chen, Yuchen Zhang, Quanjun Ge, Xiuting Liu, Yang Chen, Zhenyu State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing210093 China School of Computer Science and Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore

(Source) code search is widely concerned by software engineering researchers because it can improve the productivity and quality of software development. Given a functionality requirement usually described in a natural language sentence, a code search system can retrieve code snippets that satisfy the requirement from a large-scale code corpus, e.g., GitHub. To realize effective and efficient code search, many techniques have been proposed successively. These techniques improve code search performance mainly by optimizing three core components, including query understanding component, code understanding component, and query-code matching component. In this paper, we provide a 3-dimensional perspective survey for code search. Specifically, we categorize existing code search studies into query-end optimization techniques, code-end optimization techniques, and match-end optimization techniques according to the specific components they optimize. Considering that each end can be optimized independently and contributes to the code search performance, we treat each end as a dimension. Therefore, this survey is 3-dimensional in nature, and it provides a comprehensive summary of each dimension in detail. To understand the research trends of the three dimensions in existing code search studies, we systematically review 68 relevant literatures. Different from existing code search surveys that only focus on the query end or code end or introduce various aspects shallowly (including codebase, evaluation metrics, modeling technique, etc.), our survey provides a more nuanced analysis and review of the evolution and development of the underlying techniques used in the three ends. Based on a systematic review and summary of existing work, we outline several open challenges and opportunities at the three ends that remain to be addressed in future *** Codes 68-04 © 2023, CC BY.

关键词： Deep learning

Exploring Flat Minima for Domain Generalization with Large Learning Rates

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Jian Qi, Lei Shi, Yinghuan Gao, Yang the State Key Laboratory for Novel Software Technology National Institute of Healthcare Data Science Nanjing University Nanjing210023 China The School of Computer Science and Engineering Southeast University Nanjing211189 China

Domain Generalization (DG) aims to generalize to arbitrary unseen domains. A promising approach to improve model generalization in DG is the identification of flat minima. One typical method for this task is SWAD, which involves averaging weights along the training trajectory. However, the success of weight averaging depends on the diversity of weights, which is limited when training with a small learning rate. Instead, we observe that leveraging a large learning rate can simultaneously promote weight diversity and facilitate the identification of flat regions in the loss landscape. However, employing a large learning rate suffers from the convergence problem, which cannot be resolved by simply averaging the training weights. To address this issue, we introduce a training strategy called Lookahead which involves the weight interpolation, instead of average, between fast and slow weights. The fast weight explores the weight space with a large learning rate, which is not converged while the slow weight interpolates with it to ensure the convergence. Besides, weight interpolation also helps identify flat minima by implicitly optimizing the local entropy loss that measures flatness. To further prevent overfitting during training, we propose two variants to regularize the training weight with weighted averaged weight or with accumulated history weight. Taking advantage of this new perspective, our methods achieve state-of-the-art performance on both classification and semantic segmentation domain generalization benchmarks. The code is available at https://***/koncle/DG-with-Large-LR. Copyright © 2023, The Authors. All rights reserved.

关键词： Interpolation

DR-Tune: Improving Fine-tuning of Pretrained Visual Models by Distribution Regularization with Semantic Calibration

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Nan Chen, Jiaxin Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

关键词： Semantics

Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization

学校读者我要写书评

暂无评论

Generalizable Decision Boundaries: Dualistic Meta-Learning f...

International Conference on computer Vision (ICCV)

作者： Xiran Wang Jian Zhang Lei Qi Yinghuan Shi Nanjing University State Key Laboratory for Novel Software Technology and National Institute of Healthcare Data Science Nanjing University China Southeast University School of Computer Science and Engineering Southeast University China

Domain generalization (DG) is proposed to deal with the issue of domain shift, which occurs when statistical differences exist between source and target domains. However, most current methods do not account for a common realistic scenario where the source and target domains have different classes. To overcome this deficiency, open set domain generalization (OSDG) then emerges as a more practical setting to recognize unseen classes in unseen domains. An intuitive approach is to use multiple one-vs-all classifiers to define decision boundaries for each class and reject the outliers as unknown. However, the significant class imbalance between positive and negative samples often causes the boundaries biased towards positive ones, resulting in misclassification for known samples in the unseen target domain. In this paper, we propose a novel meta-learning-based framework called dualistic MEta-learning with joint DomaIn-Class matching (MEDIC), which considers gradient matching towards inter-domain and inter-class splits simultaneously to find a generalizable boundary balanced for all tasks. Experimental results demonstrate that MEDIC not only outperforms previous methods in open set scenarios, but also maintains competitive close set generalization ability at the same time. Our code is available at https://***/zzwdx/MEDIC.

关键词：

Understanding Heterophily for Graph Neural Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Junfu Guo, Yuanfang Yang, Liang Wang, Yunhong State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Shen Yuan Honors College Beihang University Beijing China School of Artificial Intelligence Hebei University of Technology Tianjin China

Graphs with heterophily have been regarded as challenging scenarios for Graph Neural Networks (GNNs), where nodes are connected with dissimilar neighbors through various patterns. In this paper, we present theoretical understandings of heterophily for GNNs by incorporating the graph convolution (GC) operations into fully connected networks via the proposed Heterophilous Stochastic Block Models (HSBM), a general random graph model that can accommodate diverse heterophily patterns. Our theoretical investigation comprehensively analyze the impact of heterophily from three critical aspects. Firstly, for the impact of different heterophily patterns, we show that the separability gains are determined by two factors, i.e., the Euclidean distance of the neighborhood distributions and pE [deg], where E [deg] is the averaged node degree. Secondly, we show that the neighborhood inconsistency has a detrimental impact on separability, which is similar to degrading E [deg] by a specific factor. Finally, for the impact of stacking multiple layers, we show that the separability gains are determined by the normalized distance of the lpowered neighborhood distributions, indicating that nodes still possess separability in various regimes, even when over-smoothing occurs. Extensive experiments on both synthetic and real-world data verify the effectiveness of our theory. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

TransformCode: A Contrastive Learning Framework for Code Embedding via Subtree Transformation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xian, Zixiang Huang, Rubing Towey, Dave Fang, Chunrong Chen, Zhenyu School of Computer Science and Engineering Macau University of Science and Technology Taipa999078 China School of Computer Science University of Nottingham Ningbo China Zhejiang Ningbo315100 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210093 China

Artificial intelligence (AI) has revolutionized software engineering (SE) by enhancing software development efficiency. The advent of pre-trained models (PTMs) leveraging transfer learning has significantly advanced AI for SE. However, existing PTMs that operate on individual code tokens suffer from several limitations: They are costly to train and fine-tune;and they rely heavily on labeled data for fine-tuning on task-specific datasets In this paper, we present TransformCode, a novel framework that learns code embeddings in a contrastive learning manner. Our framework is encoder-agnostic and language-agnostic, which means that it can leverage any encoder model and handle any programming language. We also propose a novel data-augmentation technique called abstract syntax tree (AST) transformation, which applies syntactic and semantic transformations to the original code snippets, to generate more diverse and robust samples for contrastive learning. Our framework has several advantages over existing methods: (1) It is flexible and adaptable, because it can easily be extended to other downstream tasks that require code representation (such as code-clone detection and classification);(2) it is efficient and scalable, because it does not require a large model or a large amount of training data, and it can support any programming language;(3) it is not limited to unsupervised learning, but can also be applied to some supervised learning tasks by incorporating task-specific labels or objectives;and (4) it can also adjust the number of encoder parameters based on computing resources. We evaluate our framework on several code-related tasks, and demonstrate its effectiveness and superiority over the state-of-the-art methods such as SourcererCC, Code2vec, and InferCode. © 2023, CC BY.

关键词： Semantics

Few-shot font style transfer with multiple style encoders

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2022年第6期65卷 83-84页

作者： Kejun ZHANG Rui ZHANG Yonglin WU Yifei LI Yonggen LING Bolin WANG Lingyun SUN Yingming LI State Key Lab of CAD&CG Zhejiang University School of Software Technology Zhejiang University Robotics X Tencent College of Information Science & Electronic Engineering Zhejiang University

Dear editor,From the sketch to an encapsulated font, text font design is a labor-intensive and time-consuming process that relies heavily on the expertise of designers and usually takes months,even years, for a professional institution. This scenario is particularly prominent for glyph-rich scripts, such as Chinese, where each character is composed of varying numbers of highly complex structured components.

关键词： Font Generation Image-to-Image Translation GANs Multi-task Learning Font Fusion Style Transfer

OcTr: Octree-based Transformer for 3D Object Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Chao Zhang, Yanan Chen, Jiaxin Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

关键词： Object detection