检索结果-内蒙古大学图书馆

LRNNET: A LIGHT-WEIGHTED NETWORK WITH EFFICIENT REDUCED NON-LOCAL OPERATION FOR REAL-TIME SEMANTIC SEGMENTATION

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Jiang, Weihao Xie, Zhaozhi Li, Yaoyi Liu, Chang Lu, Hongtao Department of Computer Science and Engineering MoE Key Lab of Articial Intelligence AI Institute Shanghai Jiao Tong University China

The recent development of light-weighted neural networks has promoted the applications of deep learning under resource constraints and mobile applications. Many of these applications need to perform a real-time and efficient prediction for semantic segmentation with a light-weighted network. This paper introduces a light-weighted network with an efficient reduced non-local module (LRNNet) for efficient and real-time semantic segmentation. We proposed a factorized convolutional block in ResNet-Style encoder to achieve more light-weighted, efficient and powerful feature extraction. Meanwhile, our proposed reduced non-local module utilizes spatial regional dominant singular vectors to achieve reduced and more representative non-local feature integration with much lower computation and memory cost. Experiments demonstrate our superior trade-off among light-weight, speed, computation and accuracy. Without additional processing and pretraining, LRNNet achieves 72.2% mIoU on Cityscapes test dataset only using the fine annotation data for training with only 0.68M parameters and with 71 FPS on a GTX 1080Ti card. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yang, Xue Yan, Junchi Ming, Qi Wang, Wentao Zhang, Xiaopeng Tian, Qi Department of Computer Science and Engineering Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China Huawei Inc. China School of Automation Beijing Institute of Technology China

Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design. In this paper, we propose a novel regression loss based on Gaussian Wasserstein distance as a fundamental approach to solve the problem. Specifically, the rotated bounding box is converted to a 2-D Gaussian distribution, which enables to approximate the indifferentiable rotational IoU induced loss by the Gaussian Wasserstein distance (GWD) which can be learned efficiently by gradient back-propagation. GWD can still be informative for learning even there is no overlapping between two rotating bounding boxes which is often the case for small object detection. Thanks to its three unique properties, GWD can also elegantly solve the boundary discontinuity and square-like problem regardless how the bounding box is defined. Experiments on five datasets using different detectors show the effectiveness of our approach. Codes are made public available12 Copyright © 2021, The Authors. All rights reserved.

关键词： Gaussian distribution

Unsupervised dual paraphrasing for two-stage semantic parsing

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Cao, Ruisheng Zhu, Su Yang, Chenyu Liu, Chen Ma, Rao Zhao, Yanbin Chen, Lu Yu, Kai MoE Key Lab of Artificial Intelligence SpeechLab Department of Computer Science and Engineering AI Institute Shanghai Jiao Tong University China

One daunting problem for semantic parsing is the scarcity of annotation. aiming to reduce nontrivial human labor, we propose a two-stage semantic parsing framework, where the first stage utilizes an unsupervised paraphrase model to convert an unlabeled natural language utterance into the canonical utterance. The downstream naive semantic parser accepts the intermediate output and returns the target logical form. Furthermore, the entire training process is split into two phases: pre-training and cycle learning. Three tailored self-supervised tasks are introduced throughout training to activate the unsupervised paraphrase model. Experimental results on benchmarks OVERNIGHT and GEOGRANNO demonstrate that our framework is effective and compatible with supervised training. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecasting

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Longyuan Zhang, Jihai Yan, Junchi Jin, Yaohui Zhang, Yunhao Duan, Yanjie Tian, Guangjian MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China State Key Lab of Advanced Optical Communication System and Network Shanghai Jiao Tong University China Department of Computer Science and Engineering Shanghai Jiao Tong University China Huawei Noah’s Ark Lab China

Time-series is ubiquitous across applications, such as transportation, finance and healthcare. Time-series is often influenced by external factors, especially in the form of asynchronous events, making forecasting difficult. However, existing models are mainly designated for either synchronous time-series or asynchronous event sequence, and can hardly provide a synthetic way to capture the relation between them. We propose Variational Synergetic Multi-Horizon Network (VSMHN), a novel deep conditional generative model. To learn complex correlations across heterogeneous sequences, a tailored encoder is devised to combine the advances in deep point processes models and variational recurrent neural networks. In addition, an aligned time coding and an auxiliary transition scheme are carefully devised for batched training on unaligned sequences. Our model can be trained effectively using stochastic variational inference and generates probabilistic predictions with Monte-Carlo simulation. Furthermore, our model produces accurate, sharp and more realistic probabilistic forecasts. We also show that modeling asynchronous event sequences is crucial for multi-horizon time-series forecasting. © 2021, CC BY.

关键词： Time series

LGESQL: Line graph enhanced text-to-sql model with mixed local and non-local relations

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cao, Ruisheng Chen, Lu Chen, Zhi Zhao, Yanbin Zhu, Su Yu, Kai X-LANCE Lab Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai Jiao Tong University Shanghai China State Key Lab of Media Convergence Production Technology and Systems Beijing China AISpeech Co. Ltd. Suzhou China

This work aims to tackle the challenging heterogeneous graph encoding problem in the text-to-SQL task. Previous methods are typically node-centric and merely utilize different weight matrices to parameterize edge types, which 1) ignore the rich semantics embedded in the topological structure of edges, and 2) fail to distinguish local and non-local relations for each node. To this end, we propose a Line Graph Enhanced Text-to-SQL (LGESQL) model to mine the underlying relational features without constructing meta-paths. By virtue of the line graph, messages propagate more efficiently through not only connections between nodes, but also the topology of directed edges. Furthermore, both local and non-local relations are integrated distinctively during the graph iteration. We also design an auxiliary task called graph pruning to improve the discriminative capability of the encoder. Our framework achieves state-of-the-art results (62.8% with GLOVE, 72.0% with ELECTRA) on the cross-domain text-to-SQL benchmark Spider at the time of writing. Copyright © 2021, The Authors. All rights reserved.

关键词： Iterative methods

A Diverse and Effective Retrieval-Based Debt Collection System with Expert Knowledge

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Luo, Jiaming Luo, Weiyi Sun, Guoqing Zhu, Mengchen Tang, Haifeng Lan, Kunyao Wu, Mengyue Zhu, Kenny Q. X-LANCE Lab Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China China Merchants Bank Credit Card Center Shanghai China University of Texas at Arlington ArlingtonTX United States

Designing effective debt collection systems is crucial for improving operational efficiency and reducing costs in the financial industry. However, the challenges of maintaining script diversity, contextual relevance, and coherence make this task particularly difficult. This paper presents a debt collection system based on real debtor-collector data from a major commercial bank. We construct a script library from real-world debt collection conversations, and propose a two-stage retrieval based response system for contextual relevance. Experimental results show that our system improves script diversity, enhances response relevance, and achieves practical dep.oyment efficiency through knowledge distillation. This work offers a scalable and automated solution, providing valuable insights for advancing debt collection practices in real-world applications. Copyright © 2025, The Authors. All rights reserved.

关键词：

Jointly encoding word confusion network and dialogue context with BERT for spoken language understanding

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Chen Zhu, Su Zhao, Zijian Cao, Ruisheng Chen, Lu Yu, Kai MoE Key Lab of Artificial Intelligence SpeechLab Department of Computer Science and Engineering AI Institute Shanghai Jiao Tong University China

Spoken Language Understanding (SLU) converts hypotheses from automatic speech recognizer (ASR) into structured semantic representations. ASR recognition errors can severely degenerate the performance of the subsequent SLU module. To address this issue, word confusion networks (WCNs) have been used to encode the input for SLU, which contain richer information than 1-best or n-best hypotheses list. To further eliminate ambiguity, the last system act of dialogue context is also utilized as additional input. In this paper, a novel BERT based SLU model (WCN-BERT SLU) is proposed to encode WCNs and the dialogue context jointly. It can integrate both structural information and ASR posterior probabilities of WCNs in the BERT architecture. Experiments on DSTC2, a benchmark of SLU, show that the proposed method is effective and can outperform previous state-of-the-art models significantly. Copyright © 2020, The Authors. All rights reserved.

关键词： Network coding

Graduated assignment for joint multi-graph matching and clustering with application to unsupervised graph matching network learning 20

学校读者我要写书评

暂无评论

Graduated assignment for joint multi-graph matching and clus...

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Runzhong Wang Junchi Yan Xiaokang Yang Department of Computer Science and Engineering Shanghai Jiao Tong University and MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University

ISBN: (纸本)9781713829546

This paper considers the setting of jointly matching and clustering multiple graphs belonging to different groups, which naturally rises in many realistic problems. Both graph matching and clustering are challenging (NP-hard) and a joint solution is appealing due to the natural connection of the two tasks. In this paper, we resort to a graduated assignment procedure for soft matching and clustering over iterations, whereby the two-way constraint and clustering confidence are modulated by two separate annealing parameters, respectively. Our technique can be further utilized for end-to-end learning whose loss refers to the cross-entropy between two lines of matching pipelines, as such the keypoint feature extraction CNNs can be learned without ground-truth supervision. Experimental results on real-world benchmarks show our method outperforms learning-free algorithms and performs comparatively against two-graph based supervised graph matching approaches. Source code is publicly available as a module of ThinkMatch.

关键词：

External attention assisted multi-phase splenic vascular injury segmentation with limited data

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhou, Yuyin Dreizin, David Wang, Yan Liu, Fengze Shen, Wei Yuille, Alan L. Department of Computer Science and Engineering University of California Santa CruzCA95064 United States Dept of Radiology R Adams Cowley Shock Trauma Center University of Maryland BaltimoreMD21201 United States Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai200241 China Department of Computer Science The Johns Hopkins University BaltimoreMD21218 United States MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

The spleen is one of the most commonly injured solid organs in blunt abdominal trauma. The development of automatic segmentation systems from multi-phase CT for splenic vascular injury can augment severity grading for improving clinical decision support and outcome prediction. However, accurate segmentation of splenic vascular injury is challenging for the following reasons: 1) Splenic vascular injury can be highly variant in shape, texture, size, and overall appearance;and 2) Data acquisition is a complex and expensive procedure that requires intensive efforts from both data scientists and radiologists, which makes large-scale well-annotated datasets hard to acquire in general. In light of these challenges, we hereby design a novel framework for multi-phase splenic vascular injury segmentation, especially with limited data. On the one hand, we propose to leverage external data to mine pseudo splenic masks as the spatial attention, dubbed external attention, for guiding the segmentation of splenic vascular injury. On the other hand, we develop a synthetic phase augmentation module, which builds upon generative adversarial networks, for populating the internal data by fully leveraging the relation between different phases. By jointly enforcing external attention and populating internal data representation during training, our proposed method outperforms other competing methods and substantially improves the popular Deeplab-v3+ baseline by more than 7% in terms of average DSC, which confirms its effectiveness. Copyright © 2022, The Authors. All rights reserved.

关键词： Data acquisition