Filters








9,325 Hits in 4.7 sec

Multi-Label Zero-Shot Learning with Structured Knowledge Graphs [article]

Chung-Wei Lee, Wei Fang, Chih-Kuan Yeh, Yu-Chiang Frank Wang
2018 arXiv   pre-print
With such investigation of structured knowledge graphs for visual reasoning, we show that our model can be applied for solving multi-label classification and ML-ZSL tasks.  ...  In this paper, we propose a novel deep learning architecture for multi-label zero-shot learning (ML-ZSL), which is able to predict multiple unseen class labels for each input instance.  ...  Extending from multi-label classification, multi-label zero-shot learning (ML-ZSL) is a branch of zero-shot learning (ZSL), which require the prediction of unseen labels which are not defined during training  ... 
arXiv:1711.06526v2 fatcat:jssexvmbwzhctou7jy5n7jo24i

Multi-label Zero-Shot Learning with Structured Knowledge Graphs

Chung-Wei Lee, Wei Fang, Chih-Kuan Yeh, Yu-Chiang Frank Wang
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
With such investigation of structured knowledge graphs for visual reasoning, we show that our model can be applied for solving multi-label classification and ML-ZSL tasks.  ...  In this paper, we propose a novel deep learning architecture for multi-label zero-shot learning (ML-ZSL), which is able to predict multiple unseen class labels for each input instance.  ...  Extending from multi-label classification, multi-label zero-shot learning (ML-ZSL) is a branch of zero-shot learning (ZSL), which require the prediction of unseen labels which are not defined during training  ... 
doi:10.1109/cvpr.2018.00170 dblp:conf/cvpr/LeeFYW18 fatcat:nspq2q7e7bhnnf3svks4yi4cpi

Multi-label Few/Zero-shot Learning with Knowledge Aggregated from Multiple Label Graphs [article]

Jueqing Lu, Lan Du, Ming Liu, Joanna Dipnall
2020 arXiv   pre-print
can benefit multi-label zero/few-shot document classification.  ...  on few/zero-shot labels.  ...  Experiments on three real-world datasets show that neural classifiers equipped with our multi-graph knowledge aggregation model can significantly improve the few/zero-shot classification performance.  ... 
arXiv:2010.07459v1 fatcat:dd5tkzft3rdgvkqzrgyjfgv5ye

Transductive Multi-class and Multi-label Zero-shot Learning [article]

Yanwei Fu, Yongxin Yang, Timothy M. Hospedales, Tao Xiang, Shaogang Gong
2015 arXiv   pre-print
Recently, zero-shot learning (ZSL) has received increasing interest.  ...  In this paper we discuss two related lines of work improving the conventional approach: exploiting transductive learning ZSL, and generalising ZSL to the multi-label case.  ...  We propose a novel framework for multi-label zero-shot learning [9] .  ... 
arXiv:1503.07884v1 fatcat:or4zahtjj5atpoxks5n4dilega

Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge [article]

He Huang, Yuanwei Chen, Wei Tang, Wenhao Zheng, Qing-Guo Chen, Yao Hu, Philip Yu
2020 arXiv   pre-print
To address these difficult issues, this paper introduces a novel multi-label zero-shot classification framework by learning to transfer from external knowledge.  ...  Multi-label zero-shot classification aims to predict multiple unseen class labels for an input image. It is more challenging than its single-label counterpart.  ...  Some studies [7, 8, 14, 17, 18, 22, 35] try to solve the multi-label zero-shot learning problem by leveraging word embeddings [35] or constructing structured knowledge graphs [14] .  ... 
arXiv:2007.15610v2 fatcat:5dqtojkavjb25g4yrp42xb4tge

Zero-Shot Ingredient Recognition by Multi-Relational Graph Convolutional Network

Jingjing Chen, Liangming Pan, Zhipeng Wei, Xiang Wang, Chong-Wah Ngo, Tat-Seng Chua
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
More specifically, we introduce multi-relational GCN (graph convolutional network) that integrates ingredient hierarchy, attribute as well as co-occurrence for zero-shot ingredient recognition.  ...  Therefore, in this paper, we target the problem of ingredient recognition with zero training samples.  ...  Compared with single-label zero-shot learning, multi-label zero-shot learning receives less attention.  ... 
doi:10.1609/aaai.v34i07.6626 fatcat:47emjeg2sjb3bjtlx7iwwr3roa

Transfer Learning in a Transductive Setting

Marcus Rohrbach, Sandra Ebert, Bernt Schiele
2013 Neural Information Processing Systems  
More specifically we adapt a graph-based learning algorithm -so far only used for semi-supervised learningto zero-shot and few-shot learning.  ...  In this work, we extend transfer learning with semi-supervised learning to exploit unlabeled instances of (novel) categories with no or only a few labeled instances.  ...  Most notably we achieve 83.7% AUC / 42.7% multi-class accuracy on the Animals with Attributes dataset for zero-shot recognition, scale to 200 unseen classes on ImageNet, and achieve up to 34.4% (+12.0%  ... 
dblp:conf/nips/RohrbachES13 fatcat:b3mufpaek5dqnfqogtaqbf3jzm

Transductive Multi-View Zero-Shot Learning

Yanwei Fu, Timothy M. Hospedales, Tao Xiang, Shaogang Gong
2015 IEEE Transactions on Pattern Analysis and Machine Intelligence  
To overcome this problem, a novel heterogeneous multi-view hypergraph label propagation method is formulated for zero-shot learning in the transductive embedding space.  ...  Most existing zero-shot learning approaches exploit transfer learning via an intermediate-level semantic representation shared between an annotated auxiliary dataset and a target dataset with different  ...  Thus the difference between zero-shot and N-shot learning lies only on the initial labelled instances: Zero-shot learning has the prototypes as labelled nodes; N-shot has instances as labelled nodes; and  ... 
doi:10.1109/tpami.2015.2408354 pmid:26440271 fatcat:eazqbmoc6vholji7ke6yyis5wq

Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation [chapter]

Yanwei Fu, Timothy M. Hospedales, Tao Xiang, Zhenyong Fu, Shaogang Gong
2014 Lecture Notes in Computer Science  
Most existing zero-shot learning approaches exploit transfer learning via an intermediate-level semantic representation such as visual attributes or semantic word vectors.  ...  In this paper we identify an inherent limitation with this approach.  ...  classes with no training example, i.e. zero-shot learning.  ... 
doi:10.1007/978-3-319-10605-2_38 fatcat:clv6flbs4najfoxbhyfucgsxhy

Knowledge Extraction in Low-Resource Scenarios: Survey and Perspective [article]

Shumin Deng, Ningyu Zhang, Hui Chen, Feiyu Xiong, Jeff Z. Pan, Huajun Chen
2022 arXiv   pre-print
Knowledge Extraction (KE) which aims to extract structural information from unstructured texts often suffers from data scarcity and emerging unseen types, i.e., low-resource scenarios.  ...  Multi-task Learning (2) Knowledge Graph (KG) have leveraged FrameNet 2 to improve EE since frames defined in FrameNet share highly similar structures with events in ACE 3 EE program.  ...  a zero-shot learning method.  ... 
arXiv:2202.08063v1 fatcat:2q64tx2mzne53gt24adi6ymj7a

Topological Transduction for Hybrid Few-shot Learning

Jiayi Chen, Aidong Zhang
2022 Proceedings of the ACM Web Conference 2022  
Few-shot learning (FSL) has attracted significant research attention for dealing with scarcely labeled concepts.  ...  from both labeled and unlabeled data to enrich the knowledge about the task-specific data distribution and multi-space relationships.  ...  In contrast, the graph structure of our task is not given, and moreover, we generalize the graph structure knowledge across unlimited graphs and adapt the graph learning procedure over different tasks.  ... 
doi:10.1145/3485447.3512033 fatcat:o4jes64ec5hhfhoffrxx57j5fa

MetaConcept: Learn to Abstract via Concept Graph for Weakly-Supervised Few-Shot Learning [article]

Baoquan Zhang, Ka-Cheong Leung, Yunming Ye, Xutao Li
2021 arXiv   pre-print
In this paper, we explore the concept hierarchy knowledge by leveraging concept graph, and take the concept graph as explicit meta-knowledge for the base learner, instead of learning implicit meta-knowledge  ...  Specifically, we firstly propose a novel regularization with multi-level conceptual abstraction to constrain a meta-learner to learn to abstract concepts via the concept graph (i.e. identifying the concepts  ...  semantics) which is useful for distinguishing categories with similiar graph structure; 2) the category graph is extracted from knowledge graph (e.g.  ... 
arXiv:2007.02379v2 fatcat:fzsqgk6btfeq7ayilukdbjop4u

A Survey on Visual Transfer Learning using Knowledge Graphs [article]

Sebastian Monka, Lavdim Halilaj, Achim Rettinger
2022 arXiv   pre-print
KGs can represent auxiliary knowledge either in an underlying graph-structured schema or in a vector-based knowledge graph embedding.  ...  , such as directed labeled graphs, hypergraphs, and hyper-relational graphs.  ...  Zero-Shot Learning is a visual transfer learning task with labeled source domain data and unlabeled target domain data.  ... 
arXiv:2201.11794v1 fatcat:tapql5h4j5dvrnxjkaxek2cquu

Learning Graph Embeddings for Compositional Zero-shot Learning

Muhammad Ferjad Naeem, Yongqin Xian, Federico Tombari, Zeynep Akata
2021 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
The key to our approach is exploiting the dependency between states, objects and their compositions within a graph structure to enforce the relevant knowledge transfer from seen to unseen compositions.  ...  In compositional zero-shot learning, the goal is to recognize unseen compositions (e.g. old dog) of observed visual primitives states (e.g. old, cute) and objects (e.g. car, dog) in the training set.  ...  Conclusion We propose a novel graph formulation for Compositional Zero-shot learning in the challenging generalized zero-shot setting.  ... 
doi:10.1109/cvpr46437.2021.00101 fatcat:zzeohcixz5h7pirypc33m6dsqe

Multi-Label Zero-Shot Learning with Transfer-Aware Label Embedding Projection [article]

Meng Ye, Yuhong Guo
2018 arXiv   pre-print
, while simultaneously learning a max-margin multi-label classifier with the projected label embeddings.  ...  Much effort on zero-shot learning however has focused on the standard multi-class setting, the more challenging multi-label zero-shot problem has received limited attention.  ...  multi-label zero-shot learning.  ... 
arXiv:1808.02474v1 fatcat:dov2w7ofbvdg3kdfiprkb5sm3i
« Previous Showing results 1 — 15 out of 9,325 results