Filters








510,885 Hits in 4.2 sec

Dynamic Instance Domain Adaptation [article]

Zhongying Deng, Kaiyang Zhou, Da Li, Junjun He, Yi-Zhe Song, Tao Xiang
2022 arXiv   pre-print
Feature alignment across domains is thus redundant. Instead, we propose to perform dynamic instance domain adaptation (DIDA).  ...  Concretely, a dynamic neural network with adaptive convolutional kernels is developed to generate instance-adaptive residuals to adapt domain-agnostic deep features to each individual instance.  ...  Instead, we propose to perform dynamic instance domain adaptation (DIDA).  ... 
arXiv:2203.05028v2 fatcat:oollro63b5ho5kp3uqtguevlym

An intelligent connector based framework for dynamic architecture

Xin Peng, Wenyun Zhao, Liang Zhang, Yijian Wu
2005 The Fifth International Conference on Computer and Information Technology (CIT'05)  
Ontology is introduced to provide the common base for communication and auto-adaptation. The domain ontology also provides a knowledge base for event inference and service assembling.  ...  An intelligent connector based framework for dynamic architecture is proposed, in which the global agent and connector agents can perform auto-adaptation on the system-level and component-level respectively  ...  Adaptable systems provide open ability of dynamic reconfiguration for external actors.  ... 
doi:10.1109/cit.2005.73 dblp:conf/IEEEcit/PengZZW05 fatcat:3tai5zz3fvb6llynb7bvylowlu

Instance Weighting for Neural Machine Translation Domain Adaptation

Rui Wang, Masao Utiyama, Lemao Liu, Kehai Chen, Eiichiro Sumita
2017 Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing  
In this paper, two instance weighting technologies, i.e., sentence weighting and domain weighting with a dynamic weight learning strategy, are proposed for NMT domain adaptation.  ...  Instance weighting has been widely applied to phrase-based machine translation domain adaptation.  ...  Conclusion and Future Work In this paper, we proposed two straightforward instance weighting methods with a dynamic weight learning strategy for NMT domain adaptation.  ... 
doi:10.18653/v1/d17-1155 dblp:conf/emnlp/WangULCS17 fatcat:kkhaw4b6w5chnfmiuutc6sejba

Dynamic Domain Generalization [article]

Zhishu Sun, Zhifeng Shen, Luojun Lin, Yuanlong Yu, Zhifeng Yang, Shicai Yang, Weijie Chen
2022 arXiv   pre-print
To tackle this problem, we develop a brand-new DG variant, namely Dynamic Domain Generalization (DDG), in which the model learns to twist the network parameters to adapt the data from different domains  ...  To enable this process, DomainMix is exploited to simulate data from diverse domains during teaching the meta-adjuster to adapt to the upcoming agnostic target domains.  ...  DDG mainly focuses on learning to twist the network parameters to adapt the instances from diverse novel domains. In this paper, each instance is assumed to be an independent latent domain.  ... 
arXiv:2205.13913v1 fatcat:k75uecf2ivh5plzmirpfhauij4

OWPA: An Ontology-Based Approach to Adaptable Workflow Participant Assignment

Jianmei GUO, Yinglin WANG, Jian CAO
2010 IEICE transactions on information and systems  
Moreover, OWPA is bound to the workflow modeling tool and the workflow monitor respectively to adapt to dynamic workflow modification in workflow definitions and workflow instances.  ...  OWPA introduces domain ontology to organize the enterprise data and uses a welldefined OWPA rule to express an authorization constraint.  ...  They, however, are not adaptable to dynamic workflow modification, especially workflow instance modification.  ... 
doi:10.1587/transinf.e93.d.1572 fatcat:mvjlntm6bjgpthj2a47bwoewau

Dynamic adaptation of service-based applications: a design for adaptation approach

Martina De Sanctis, Antonio Bucchiarone, Annapaola Marconi
2020 Journal of Internet Services and Applications  
The proposed approach has been implemented and evaluated in a real-world case study in the mobility domain.  ...  of new services that can easily join the application, and (ii) the operation of applications under dynamic circumstances, to face the openness and dynamicity of the environment.  ...  Journal of Internet Services Definition 11 ( 11 Adaptive System Instance) An adaptive system instance AS I of an adaptive system AS = {o 1 , . . . , o n } is a set of domain object instances AS I = {  ... 
doi:10.1186/s13174-020-00123-6 fatcat:zbo6saksaffvfdz7nlt4e2ssee

An Approach to Dynamically Reconfiguring Service-Oriented Applications from a Business Perspective [chapter]

Jianwu Wang, Yanbo Han, Jing Wang, Gang Li
2004 Lecture Notes in Computer Science  
service-oriented application instances, which can realize the dynamic reconfiguration of service-oriented applications in a straightforward way to timely adapt to business requirement changes.  ...  to respectively express changes in the business domain and the software domain.  ...  Principle of CAFISE adapt Approach The convergence concept is firstly presented by David Taylor at 1995 to bridge the gap between the business domain and the software domain, expecting to construct software  ... 
doi:10.1007/978-3-540-30483-8_43 fatcat:gshul24tlzf2voetxhxysi3kwy

Metadata and Adaptive Object-Models [chapter]

Joseph W. Yoder, Reza Razavi
2000 Lecture Notes in Computer Science  
A way to meet such requirements is to use an Adaptive Object-Model (AOM). This paper describes common architectures for adaptive object-models and summarizes the results from our ECOOP 2000 workshop.  ...  Participants to this workshop focused on comparisons between the Adaptive Object-Model's approach and those of Reflection and Metamodeling.  ...  An instance of that specification An instance of that specification A domain-specific language A domain-specific language A system specification A system specification Type Cube (Fig. 1 ) is an example  ... 
doi:10.1007/3-540-44555-2_9 fatcat:sbulerdfefadrmp5vrn74uqx2m

Adaptive faceted browser for navigation in open information spaces

Michal Tvarozek, Maria Bielikova
2007 Proceedings of the 16th international conference on World Wide Web - WWW '07  
We propose a method of navigation in open information spaces based on an enhanced faceted browser with support for dynamic facet generation and adaptation based on user characteristics.  ...  ADAPTIVE FACETED NAVIGATION We propose the enhancement of (adaptive) faceted browsers with support for dynamic facet generation based on data stored in the domain and user ontologies.  ...  Dynamic facet generation During facet generation we examine the attributes of the desired instances within the information space as defined by the respective domain ontology.  ... 
doi:10.1145/1242572.1242825 dblp:conf/www/TvarozekB07 fatcat:gdppmq32kney7mx74ai6qadshm

Domain Adaptive Person Search [article]

Junjie Li, Yichao Yan, Guanshuo Wang, Fufu Yu, Qiong Jia, Shouhong Ding
2022 arXiv   pre-print
In this paper, we take a further step and present Domain Adaptive Person Search (DAPS), which aims to generalize the model from a labeled source domain to the unlabeled target domain.  ...  To address these challenges, we propose a strong baseline framework with two dedicated designs. 1) We design a domain alignment module including image-level and task-sensitive instance-level alignments  ...  Domain Adaptation for Person ReID Unsupervised domain adaptation (UDA) ReID [7, 10, 28, 15, 17, 32, 42] typically trains a model with labelled source domain and transfers to the target domain under the  ... 
arXiv:2207.11898v1 fatcat:pl4qnodjfbcfrgedypsj7g2g6e

Multi-Domain Neural Machine Translation through Unsupervised Adaptation

M. Amin Farajian, Marco Turchi, Matteo Negri, Marcello Federico
2017 Proceedings of the Second Conference on Machine Translation  
instances and each test sentence, dynamically sets the hyperparameters of the learning algorithm and updates the generic model on-the-fly.  ...  To tackle the weaknesses of current NMT technology in this unsupervised multi-domain setting, we explore an efficient instance-based adaptation method that, by exploiting the similarity between the training  ...  Adaptive Dynamic-Lrate).  ... 
doi:10.18653/v1/w17-4713 dblp:conf/wmt/FarajianTNF17 fatcat:dhx34uld7zhidf4zw77nguisse

Learning Heuristic Selection with Dynamic Algorithm Configuration [article]

David Speck, André Biedenkapp, Frank Hutter, Robert Mattmüller, Marius Lindauer
2021 arXiv   pre-print
To learn dynamic heuristic selection, we propose an approach based on reinforcement learning and show empirically that domain-wise learned policies, which take the internal search dynamics of a planning  ...  Since the performance of a heuristic varies from instance to instance, approaches such as algorithm selection can be successfully applied.  ...  A possible explanation is that a dynamic policy is the key to solving difficult instances in this domain.  ... 
arXiv:2006.08246v3 fatcat:3hlnm2crwzckpgnqecjhzdgh6i

Enhancing Accuracy of Hybrid Recommender Systems through Adapting the Domain Trends

Fatih Aksel, Aysenur Birtürk
2010 ACM Conference on Recommender Systems  
In this paper, we propose an adaptive method for hybrid recommender systems, in which the combination of algorithms are learned and dynamically updated from the results of previous predictions.  ...  , and adapt the combination of content-based and collaborative algorithms to have better results.  ...  Fixed strategy may be suboptimal for dynamic domains&user behaviors. Moreover they are unable to adapt to domain drifts.  ... 
dblp:conf/recsys/AkselB10 fatcat:sekiny7jsrczphnqxbgejzfq3a

Personalized Navigation in the Semantic Web [chapter]

Michal Tvarožek
2006 Lecture Notes in Computer Science  
The proposed approach takes advantage of adaptive hypermedia in an enhanced faceted browser capable of dynamically adapting the set of available facets with additional support for data retrieval from an  ...  ontology and adaptive annotation of search results.  ...  The most interesting are the facets, their dynamic generation from a domain ontology and their adaptation based on a user model.  ... 
doi:10.1007/11768012_71 fatcat:hvauepa3m5hxja3d2rnfdy54ci

Combining Adaptive Hypermedia Techniques and Ontology Reasoning to Produce Dynamic Personalized News Services [chapter]

Owen Conlan, Ian O'Keeffe, Shane Tallon
2006 Lecture Notes in Computer Science  
Applying traditional Adaptive Hypermedia techniques to the personalization of news can pose a number of problems.  ...  The first main difficulty is the fact that news is inherently dynamic, thus producing an ever shifting pool from which content can be sourced.  ...  What has changed, and is the main source of dynamism in this news domain, are the instances (and possibly number of instances). For example, the driver line ups of teams change year on year.  ... 
doi:10.1007/11768012_10 fatcat:ppjakmhgwvggven3jvtykszkbu
« Previous Showing results 1 — 15 out of 510,885 results