检索结果-内蒙古大学图书馆

GPTR: Gestalt-Perception Transformer for Diagram Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hu, Xin Zhang, Lingling Liu, Jun Fan, Jinfu You, Yang Wu, Yaqiang Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering School of Computer Science and Technology Xi’an Jiaotong University China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University China Department of Control Science and Engineering Tongji University Shanghai China Department of Computer Science National University of Singapore Singapore Lenovo Research Beijing China

Diagram object detection is the key basis of practical applications such as textbook question answering. Because the diagram mainly consists of simple lines and color blocks, its visual features are sparser than those of natural images. In addition, diagrams usually express diverse knowledge, in which there are many low-frequency object categories in diagrams. These lead to the fact that traditional data-driven detection model is not suitable for diagrams. In this work, we propose a gestalt-perception transformer model for diagram object detection, which is based on an encoder-decoder architecture. Gestalt perception contains a series of laws to explain human perception, that the human visual system tends to perceive patches in an image that are similar, close or connected without abrupt directional changes as a perceptual whole object. Inspired by these thoughts, we build a gestalt-perception graph in transformer encoder, which is composed of diagram patches as nodes and the relationships between patches as edges. This graph aims to group these patches into objects via laws of similarity, proximity, and smoothness implied in these edges, so that the meaningful objects can be effectively detected. The experimental results demonstrate that the proposed GPTR achieves the best results in the diagram object detection task. Our model also obtains comparable results over the competitors in natural image object detection. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

Protein Structure Prediction Using A New Optimization-Based Evolutionary and Explainable Artificial Intelligence Approach

学校读者我要写书评

暂无评论

IEEE Transactions on Evolutionary Computation 2024年第3期29卷 1-1页

作者： Hong, Jun Zhan, Zhi-Hui He, Langchong Xu, Zongben Zhang, Jun School of Computer Science and Engineering South China University of Technology Guangzhou P. R. China Health Science Center School of Pharmacy Xi’an Jiaotong University Xi’an P. R. China National Engineering Laboratory for Big Data Analytics Xi’an Jiaotong University Xi’an P. R. China College of Artificial Intelligence Nankai University Tianjin P. R. China

Protein structure prediction (PSP) is an important scientific problem because it helps humans to understand how proteins perform their biological functions. This paper models the PSP problem as a multi-objective optimization problem with three fast and accurate knowledge-based energy functions. This way, using evolutionary computation (EC)-based artificial intelligence (AI) approach to solve this multi-objective PSP problem to find the optimal structure is explainable. Considering that the multiple populations for multiple objectives (MPMO) framework shows efficient performance in solving lots of multi-objective benchmarks and real-world problems, this paper proposes a new AI approach named improved MPMO-based differential evolution (IMPMO-DE) to solve the multi-objective PSP problem. To our best knowledge, this is the first time that MPMO is applied to PSP, with three novel strategies. First, an adaptive archive-based mutation strategy is proposed to better balance the exploration and exploitation abilities by adaptively using different archive-based mutation operators in different evolutionary stages. Second, a mixed individual transfer strategy is proposed to share search information among the multiple populations to accelerate the convergence speed. Third, an evolvable archive update strategy is proposed to generate more promising solutions through evolving the archived solutions. IMPMO-DE is tested on 28 representative proteins and all the available template-free modeling proteins up to 404 residues in the famous Critical Assessment of Protein Structure Prediction (CASP14) competition. Experimental results show that IMPMO-DE performs better than the compared state-of-the-art EC-based PSP methods and ranks above average compared with all the CASP14 competitors. More importantly, IMPMO-DE is a new efficient AI approach that opens a promising optimization-based evolutionary and explainable way for efficient PSP rather than deep learning approaches like AlphaFold2,

关键词： Evolutionary algorithms

Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Fangzhi Liu, Jun Lin, Qika Pan, Yudai Zhang, Lingling School of Computer Science and Technology Xi'an Jiaotong University Xi'an China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech. R&d National Engineering Lab for Big Data Analytics Xi'an China

Machine reading comprehension has aroused wide concerns, since it explores the potential of model for text understanding. To further equip the machine with the reasoning capability, the challenging task of logical reasoning is proposed. Previous works on logical reasoning have proposed some strategies to extract the logical units from different aspects. However, there still remains a challenge to model the long distance dependency among the logical units. Also, it is demanding to uncover the logical structures of the text and further fuse the discrete logic to the continuous text embedding. To tackle the above issues, we propose an end-to-end model Logiformer which utilizes a two-branch graph transformer network for logical reasoning of text. Firstly, we introduce different extraction strategies to split the text into two sets of logical units, and construct the logical graph and the syntax graph respectively. The logical graph models the causal relations for the logical branch while the syntax graph captures the co-occurrence relations for the syntax branch. Secondly, to model the long distance dependency, the node sequence from each graph is fed into the fully connected graph transformer structures. The two adjacent matrices are viewed as the attention biases for the graph transformer layers, which map the discrete logical structures to the continuous text embedding space. Thirdly, a dynamic gate mechanism and a question-aware self-attention module are introduced before the answer prediction to update the features. The reasoning process provides the interpretability by employing the logical units, which are consistent with human cognition. The experimental results show the superiority of our model, which outperforms the state-of-the-art single model on two logical reasoning benchmarks. © 2022, CC BY.

关键词： Embeddings

Tile Classification Based Viewport Prediction with Multi-modal Fusion Transformer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Zhihao Chen, Yiwei Zhang, Weizhan Yan, Caixia Zheng, Qinghua Wang, Qi Chen, Wangdu School of Computer Science and Technology Xi'an Jiaotong University Key Laboratory of Intelligent Networks and Network Security Ministry of Education Xi'an Jiaotong University Xi’an China School of Computer Science and Technology Xi'an Jiaotong University & National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xi’an China MIGU Video Shanghai China

Viewport prediction is a crucial aspect of tile-based 360◦ video streaming system. However, existing trajectory based methods lack of robustness, also oversimplify the process of information construction and fusion between different modality inputs, leading to the error accumulation problem. In this paper, we propose a tile classification based viewport prediction method with Multi-modal Fusion Transformer, namely MFTR. Specifically, MFTR utilizes transformer-based networks to extract the long-range dependencies within each modality, then mine intra- and inter-modality relations to capture the combined impact of user historical inputs and video contents on future viewport selection. In addition, MFTR categorizes future tiles into two categories: user interested or not, and selects future viewport as the region that contains most user interested tiles. Comparing with predicting head trajectories, choosing future viewport based on tile's binary classification results exhibits better robustness and interpretability. To evaluate our proposed MFTR, we conduct extensive experiments on two widely used PVS-HM and Xu-Gaze dataset. MFTR shows superior performance over state-of-the-art methods in terms of average prediction accuracy and overlap ratio, also presents competitive computation efficiency. © 2023, CC BY.

关键词： Forecasting

Learnable Convolutional Attention Network for Knowledge Graph Completion

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Shang, Bin Zhao, Yinliang Liu, Jun School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech. R&D Xi’an Jiaotong University Shaanxi Xi’an710049 China National Engineering Lab for Big Data Analytics Shaanxi Xi’an710049 China

Recently, graph convolutional networks (GCNs) and graph attention networks (GATs) have been widely used in knowledge graph completion (KGC), which aims to solve the incompleteness of knowledge graphs (KGs). However, GCNs based KGC models tend to stack redundant information when one entity have several noisy neighbors. GATs based KGC models may focus on certain neighbors and lead to weakening of structural information. Furthermore, relations in KGs have their specific semantics and should be considered when aggregating neighbor information (message passing). To address the above limitations, we propose a learnable convolutional attention network for knowledge graph completion named LCA-KGC. LCA-KGC introduces a knowledge graph convolutional attention network by using the convolution operation before the attention mechanism to ensure the structural information acquisition and avoid the redundant information stacking. Furthermore, to complete the autonomous switching of GNNs types and eliminate the necessity of pre-validating the local structure of KGs, LCA-KGC designs a learnable knowledge graph convolutional attention network by comprising three types of GNNs in one learnable formulation. Moreover, a learnable message function is proposed to emphasize relational semantics when aggregating neighbor information. Extensive experiments on standard KG datasets validate the effectiveness of the proposed innovations, and LCA-KGC achieves state-of-the-art (SOTA) performance compared to existing approaches (e.g., compared to SOTA approaches, LCA-KGC improves MRR from 0.360 to 0.372 on FB15k-237 dataset, and Hits@3 from 0.561 to 0.581 on YAGO3-10 dataset). © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

Generalized Category Discovery with Decoupled Prototypical Network

学校读者我要写书评

暂无评论

arXiv 2022年

作者： An, Wenbin Tian, Feng Zheng, Qinghua Ding, Wei Wang, QianYing Chen, Ping School of Automation Science and Engineering Xi’an Jiaotong University China School of Computer Science and Technology Xi’an Jiaotong University China National Engineering Laboratory for Big Data Analytics China Department of Computer Science University of Massachusetts Boston United States Lenovo Research Department of Engineering University of Massachusetts Boston United States

Generalized Category Discovery (GCD) aims to recognize both known and novel categories from a set of unlabeled data, based on another dataset labeled with only known categories. Without considering differences between known and novel categories, current methods learn about them in a coupled manner, which can hurt model’s generalization and discriminative ability. Furthermore, the coupled training approach prevents these models transferring category-specific knowledge explicitly from labeled data to unlabeled data, which can lose high-level semantic information and impair model performance. To mitigate above limitations, we present a novel model called Decoupled Prototypical Network (DPN). By formulating a bipartite matching problem for category prototypes, DPN can not only decouple known and novel categories to achieve different training targets effectively, but also align known categories in labeled and unlabeled data to transfer category-specific knowledge explicitly and capture high-level semantics. Furthermore, DPN can learn more discriminative features for both known and novel categories through our proposed Semantic-aware Prototypical Learning (SPL). Besides capturing meaningful semantic information, SPL can also alleviate the noise of hard pseudo labels through semantic-weighted soft assignment. Extensive experiments show that DPN outperforms state-of-the-art models by a large margin on all evaluation metrics across multiple benchmark datasets. Code and data are available at https://***/Lackel/DPN. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

Training networks in null space of feature covariance for continual learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Shipeng Li, Xiaorong Sun, Jian Xu, Zongben School of Mathematics and Statistics Xi’an Jiaotong University Xi’an710049 China National Engineering Laboratory of Big Data Algorithms and Analysis Technology Xi’an710049 China Pazhou Lab Guangzhou Guangdong510335 China

In the setting of continual learning, a network is trained on a sequence of tasks, and suffers from catastrophic forgetting. To balance plasticity and stability of network in continual learning, in this paper, we propose a novel network training algorithm called Adam-NSCL, which sequentially optimizes network parameters in the null space of previous tasks. We first propose two mathematical conditions respectively for achieving network stability and plasticity in continual learning. Based on them, the network training for sequential tasks can be simply achieved by projecting the candidate parameter update into the approximate null space of all previous tasks in the network training process, where the candidate parameter update can be generated by Adam. The approximate null space can be derived by applying singular value decomposition to the uncentered covariance matrix of all input features of previous tasks for each linear layer. For efficiency, the uncentered covariance matrix can be incrementally computed after learning each task. We also empirically verify the rationality of the approximate null space at each linear layer. We apply our approach to training networks for continual learning on benchmark datasets of CIFAR-100 and TinyImageNet, and the results suggest that the proposed approach outperforms or matches the state-ot-the-art continual learning approaches. © 2021, CC BY-NC-ND.

关键词： Covariance matrix

Noise-Tolerant Learning for Audio-Visual Action Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Han, Haochen Zheng, Qinghua Luo, Minnan Miao, Kaiyao Tian, Feng Chen, Yan The National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Xi’an710049 China The School of Computer Science and Technology Xi’an Jiaotong University Xi’an710049 China The Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Ministry of Education Xi’an710049 China The School of Cyber Science and Engineering Xi’an Jiaotong University Xi’an710049 China

Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the model. Although various multi-modal learning methods have been proposed and offer remarkable recognition results, almost all of these methods rely on high-quality manual annotations and assume that modalities among multi-modal data provide semantically relevant information. Unfortunately, the widely used video datasets are usually coarse-annotated or collected from the Internet. Thus, it inevitably contains a portion of noisy labels and noisy correspondence. To address this challenge, we use the audio-visual action recognition task as a proxy and propose a noise-tolerant learning framework to find anti-interference model parameters against both noisy labels and noisy correspondence. Specifically, our method consists of two phases that aim to rectify noise by the inherent correlation between modalities. First, a noise-tolerant contrastive training phase is performed to make the model immune to the possible noisy-labeled data. Despite the benefits brought by contrastive training, it would overfit the noisy correspondence and thus provide false supervision. To alleviate the influence of noisy correspondence, we propose a cross-modal noise estimation component to adjust the consistency between different modalities. As the noisy correspondence existed at the instance level, we further propose a category-level contrastive loss to reduce its interference. Second, in the hybrid-supervised training phase, we calculate the distance metric among features to obtain corrected labels, which are used as complementary supervision to guide the training. Furthermore, due to the lack of suitable datasets, we establish a benchmark of real-world noisy correspondence in audio-visual data by relabeling the Kinetics dataset. Extensive experiments on a wide range of noisy levels demonstrate that our method significant

关键词： Modal analysis

An automated workflow for integrating environmental sustainability assessment into parametric part design through standard reference models 27

学校读者我要写书评

暂无评论

An automated workflow for integrating environmental sustaina...

27th CIRP Life Cycle engineering Conference, LCE 2020

作者： Bernstein, William Z. Tensa, Melissa Praniewicz, Maxwell Kwon, Soonjo Ramanujan, Devarajan Engineering Laboratory National Institute of Standards and Technology MD United States School of Mechanical Industrial and Manufacturing Engineering Oregon State University OR United States George W. Woodruff School of Mechanical Engineering Georgia Institute of Technology AtlantaGR United States Engineering Laboratory National Institute of Standards and Technology MD United States Korea Advanced Institute of Science and Technology Daejeon Korea Republic of Mechanical Engineering Section Center for Digitalization Big Data and Data Analytics Aarhus University Aarhus8000 Denmark

Integrating environmental sustainability assessment into parametric design presents an opportunity for enabling sustainable product design. However, this is a challenging task as quantitative methods for sustainability assessment are poorly integrated with parametric design and optimization tools. Furthermore, current streamlined approaches for computing environmental impact during the design stage often ignore manufacturing-related impacts resulting from the geometric complexity of parts. To address these gaps, we present a systematic workflow for computing environmental indicators from parametric design models. Our workflow utilizes the unit manufacturing process information model to evaluate manufacturing-phase resource consumption from process planning data, and consequently enables quantitative correlation of design parameters to the calculated environmental indicators. We demonstrate our workflow through a case study involving the design of a rigid flange coupling, wherein we evaluate the influence of geometric design parameters on the corresponding environmental impact of the design. © 2020 The Author(s). Published by Elsevier B.V.

关键词： Computer aided design