检索结果-内蒙古大学图书馆

2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025

作者： Tan, Tianlong Chen, Bin Cao, Hongliang Yan, Chenggang Ma, Yike Dai, Feng Institute of Computing Technology Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Beijing China Shandong University China University of Chinese Academy of Sciences Beijing China Hangzhou Dianzi University China

ISBN: (纸本)9798331510831

Self-Supervised Semantic Segmentation, aiming to leverage masses of unlabeled data for boosting semantic segmentation, has been rapidly emerging as an active task in recent years. However, existing self-supervised semantic segmentation approaches mainly focus on planar images, leaving multiple distorted objects encountered in panoramic images unexplored due to the formidable challenge of handling heterogeneous degrees of distortions across different locations. In this paper, we propose a novel Self-Supervised Panoramic Semantic Segmentation model, termed DASC-SPT, built upon the mainstream contrastive learning framework. Towards distortions in panoramic images, we present two structures to better learn from distorted features by applying planar images. For the input images of self-supervision, we design a Spherical Projection Transformation (SPT) strategy that involves randomly projecting planar images onto various locations of the sphere to introduce the distortions. For pixel-wise distorted features, we construct a Deformation-aware Sampling Consistency (DASC) framework to further utilize the shared content and discrepancies caused by different distortions of paired views, where the deformation-aware consistency can be quantified on pixel-wise features. Both of the two components facilitate the model to adapt to distortions and boost panoramic semantic segmentation. Extensive comprehensive experiments on three panoramic datasets demonstrate the effectiveness and superiority of DASC-SPT approach. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Cross-Domain Ontology Semantic Representation Based on NCBI-BlueBERT Embedding

引用

Chinese Journal of Electronics 2022年第5期31卷 860-869页

作者： ZHAO Lingling WANG Junjie WANG Chunyu GUO Maozu Faculty of Computing Harbin Institute of Technology Department of Medical Informatics School of Biomedical Engineering and InformaticsNanjing Medical University Beijing Key Laboratory of Intelligent Processing for Building Big Data School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture

A common but critical task in biological ontologies data analysis is to compare the difference between ontologies. There have been numerous ontologybased semantic-similarity measures proposed in specific ontology domain, but it still remains a challenge for crossdomain ontologies comparison. An ontology contains the scientific natural language description for the corresponding biological aspect. Therefore, we develop a new method based on natural language processing(NLP) representation model bidirectional encoder representations from transformers(BERT) for cross-domain semantic representation of biological ontologies. This article uses the BERT model to represent the word-level of the ontologies as a set of vectors, facilitating the semantic analysis or comparing the biomedical entities named in an ontology or associated with ontology terms. We evaluated the ability of our method in two experiments: calculating similarities of pair-wise disease ontology and human phenotype ontology terms and predicting the pair-wise of proteins interaction. The experimental results demonstrated the comparative performance. This gives promise to the development of NLP methods in biological data analysis.

关键词： human phenotype ontology cross-domain semantic representation natural language description pair-wise disease ontology data analysis bidirectional encoder representations NLP protein interaction diseases proteins natural language processing ontologies (artificial intelligence) natural language processing representation neural nets bioinformatics semantic-similarity measures cross-domain ontology semantic representation semantic analysis NCBI-BlueBERT embedding biological ontology data analysis

来源：评论

学校读者我要写书评

暂无评论

DO-FAM: Disentangled Non-Linear Latent Navigation For Facial Attribute Manipulation 48

DO-FAM: Disentangled Non-Linear Latent Navigation For Facial...

引用

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Yuan, Yifan Ma, Siteng Shan, Hongming Zhang, Junping Shanghai Key Lab of Intelligent Information Processing School of Computer Science China Fudan University Institute of Science and Technology for Brain-Inspired Intelligence Shanghai China

ISBN: (纸本)9781728163277

Facial attribute manipulation (FAM) aims to edit the semantic attributes of facial images according to the user's requirements. Unfortunately, the majority of existing FAM methods struggle in meeting at least one of the two requirements: high reconstruction quality and high irrelevance preservation. To alleviate these two limitations, we propose a novel Disentangled nOn-linear latent navigation framework for FAM, termed DO-FAM. To promote the reconstruction quality, we leverage hypernetworks to fine-tune a pre-trained StyleGAN2 generator. To decouple entangled attributes, we propose a novel Disentangled nOn-Linear Latent transformation module, named DOLL, which consists of three components: (1) a decomposer to factorize input latent codes into two parts: attribute-related and attribute-unrelated;(2) a non-linear Latent Transformation Network (LTNet) to navigate the attribute-related latent codes to the target one with respect to the designed attribute(s);and (3) a latent classifier tasked with predicting latent codes' attributes to guide the latent code navigation. Extensive experimental results on a widely-used benchmark facial editing dataset, CelebA-HQ, demonstrate the superiority of our method over state-of-the-art methods. © 2023 IEEE.

关键词： disentangle learning Facial attribute manipulation Hypernetwork style transfer StyleGAN

来源：评论

学校读者我要写书评

暂无评论

Learning to Localize Cross-Anatomy Landmarks in X-Ray Images with a Universal Model

引用

Biomedical Engineering Frontiers 2022年第1期3卷 298-308页

作者： Heqin Zhu Qingsong Yao Li Xiao S.Kevin Zhou Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China Center for Medical Imaging RoboticsAnalytic Computing&Learning(MIRACLE)School of Biomedical Engineering&Suzhou Institute for Advanced ResearchUniversity of Science and Technology of ChinaSuzhou 215123China

Objective and Impact *** this work,we develop a universal anatomical landmark detection model which learns once from multiple datasets corresponding to different anatomical *** with the conventional model trained on a single dataset,this universal model not only is more light weighted and easier to train but also improves the accuracy of the anatomical landmark *** accurate and automatic localization of anatomical landmarks plays an essential role in medical image ***,recent deep learning-based methods only utilize limited data from a single *** is promising and desirable to build a model learned from different regions which harnesses the power of big *** model consists of a local network and a global network,which capture local features and global features,*** local network is a fully convolutional network built up with depth-wise separable convolutions,and the global network uses dilated convolution to enlarge the receptive field to model global *** evaluate our model on four 2D X-ray image datasets totaling 1710 images and 72 landmarks in four anatomical *** experimental results show that our model improves the detection accuracy compared to the state-of-the-art *** model makes the first attempt to train a single network on multiple datasets for landmark *** results qualitatively and quantitatively show that our proposed model performs better than other models trained on multiple datasets and even better than models trained on a single dataset separately.

关键词： convolution utilize separable

来源：评论

学校读者我要写书评

暂无评论

ETS: An Error Tolerable System for Coreference Resolution 15

ETS: An Error Tolerable System for Coreference Resolution

引用

15th Conference on Computational Natural Language Learning, CoNLL 2011

作者： Xiong, Hao Song, Linfeng Meng, Fandong Liu, Yang Liu, Qun Lü, Yajuan Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing100190 China

ISBN: (纸本)9781937284084

This paper presents our error tolerable system for coreference resolution in CoNLL-2011(Pradhan et al., 2011) shared task (closed track). Different from most previous reported work, we detect mention candidates based on packed forest instead of single parse tree, and we use beam search algorithm based on the Bell Tree to create entities. Experimental results show that our methods achieve promising results on the development set. © 2011 Association for Computational Linguistics

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Beyond MLE: Convex Learning for Text Generation 37

Beyond MLE: Convex Learning for Text Generation

引用

37th Conference on Neural information processing Systems, NeurIPS 2023

作者： Shao, Chenze Ma, Zhengrui Zhang, Min Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China School of Future Science and Engineering Soochow University China

ISBN: (纸本)9781713899921

Maximum likelihood estimation (MLE) is a statistical method used to estimate the parameters of a probability distribution that best explain the observed data. In the context of text generation, MLE is often used to train generative language models, which can then be used to generate new text. However, we argue that MLE is not always necessary and optimal, especially for closed-ended text generation tasks like machine translation. In these tasks, the goal of model is to generate the most appropriate response, which does not necessarily require it to estimate the entire data distribution with MLE. To this end, we propose a novel class of training objectives based on convex functions, which enables text generation models to focus on highly probable outputs without having to estimate the entire data distribution. We investigate the theoretical properties of the optimal predicted distribution when applying convex functions to the loss, demonstrating that convex functions can sharpen the optimal distribution, thereby enabling the model to better capture outputs with high probabilities. Experiments on various text generation tasks and models show the effectiveness of our approach. It enables autoregressive models to bridge the gap between greedy and beam search, and facilitates the learning of non-autoregressive models with a maximum improvement of 9+ BLEU points. Moreover, our approach also exhibits significant impact on large language models (LLMs), substantially enhancing their generative capability on various tasks. Source code is available at https://***/ictnlp/Convex-Learning. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Imagine Before Go: Self-Supervised Generative Map for Object Goal Navigation

Imagine Before Go: Self-Supervised Generative Map for Object...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Sixian Zhang Xinyao Yu Xinhang Song Xiaohan Wang Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The Object Goal navigation (ObjectNav) task requires the agent to navigate to a specified target in an unseen environment. Since the environment layout is unknown, the agent needs to infer the unknown contextual objects from partially observations, thereby deducing the likely location of the target. Previous end-to-end RL methods capture contextual relationships through implicit representations while they lack notion of geometry. Alternatively, modular methods construct local maps for recording the observed geometric structure of unseen environment, however, lacking the reasoning of contextual relation limits the exploration efficiency. In this work, we propose the self-supervised generative map (SGM), a modular method that learns the explicit context relation via self-supervised learning. The SGM is trained to leverage both episodic observations and general knowledge to reconstruct the masked pixels of a cropped global map. During navigation, the agent maintains an incomplete local semantic map, meanwhile, the unknown regions of the local map are generated by the pretrained SGM. Based on the generated map, the agent sets the predicted location of the target as the goal and moves towards it. Experiments on Gibson, MP3D and HM3D show the effectiveness of our method. The code is available at https://***/sx-zhang/SGM.

关键词： Training Geometry Navigation Large language models Semantics Layout Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Domain-aware Node Representation Learning for Graph Out-of-Distribution Generalization

Domain-aware Node Representation Learning for Graph Out-of-D...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yi Qiao Yang Liu Qing He Xiang Ao Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciencs Beijing China Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Graph Neural Networks (GNNs) have demonstrated impressive success across diverse fields when data satisfies in-distribution (ID) assumption. Nevertheless, GNN performance significantly declines in cases of distribution shifts between training and testing graph data. This degradation primarily stems from spurious correlations between irrelevant domain information and target labels in out-of-distribution (OOD) scenarios. Thus, maximizing the utilization of domain information becomes imperative. In light of this, we propose a novel approach named Domain-aware Node Representation Learning (DNRL), comprehensively incorporates domain information to bolster generalization capability. Specifically, DNRL selectively interpolates nodes with the same label but different domains, extending training data into unseen domains and alleviating the effects caused by domain-related spurious correlations. Futhermore, by introducing a domain-aware contrastive learning strategy, our method implicitly decouples domain information from node information to learn domain-independent node representations. Extensive experiments on graph out-of-distribution benchmarks demonstrate that DNRL can achieve effective OOD generalization performance across diverse domains.

关键词： Representation learning Training Degradation Interpolation Correlation Training data Signal processing Graph neural networks Data models Speech processing

来源：评论

学校读者我要写书评

暂无评论

Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation

Viterbi Decoding of Directed Acyclic Transformer for Non-Aut...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Shao, Chenze Ma, Zhengrui Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Non-autoregressive models achieve significant decoding speedup in neural machine translation but lack the ability to capture sequential dependency. Directed Acyclic Transformer (DA-Transformer) was recently proposed to model sequential dependency with a directed acyclic graph. Consequently, it has to apply a sequential decision process at inference time, which harms the global translation accuracy. In this paper, we present a Viterbi decoding framework for DA-Transformer, which guarantees to find the joint optimal solution for the translation and decoding path under any length constraint. Experimental results demonstrate that our approach consistently improves the performance of DA-Transformer while maintaining a similar decoding speedup. © 2022 Association for Computational Linguistics.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Improving Fake News Detection of Influential Domain via Domain- and Instance-Level Transfer 29

Improving Fake News Detection of Influential Domain via Doma...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Nan, Qiong Wang, Danding Zhu, Yongchun Sheng, Qiang Shi, Yuhui Cao, Juan Li, Jintao Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Both real and fake news in various domains, such as politics, health, and entertainment are spread via online social media every day, necessitating fake news detection for multiple domains. Among them, fake news in specific domains like politics and health has more serious potential negative impacts on the real world (e.g., the infodemic led by COVID-19 misinformation). Previous studies focus on multi-domain fake news detection, by equally mining and modeling the correlation between domains. However, these multi-domain methods suffer from a seesaw problem: the performance of some domains is often improved at the cost of hurting the performance of other domains, which could lead to an unsatisfying performance in specific domains. To address this issue, we propose a Domain- and Instance-level Transfer Framework for Fake News Detection (DITFEND), which could improve the performance of specific target domains. To transfer coarse-grained domain-level knowledge, we train a general model with data of all domains from the meta-learning perspective. To transfer fine-grained instance-level knowledge and adapt the general model to a target domain, we train a language model on the target domain to evaluate the transferability of each data instance in source domains and re-weigh each instance’s contribution. Offline experiments on two datasets demonstrate the effectiveness of DITFEND. Online experiments show that DITFEND brings additional improvements over the base models in a real-world scenario. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：