Filters








1,333 Hits in 4.6 sec

Transductive Multi-label Zero-shot Learning [article]

Yanwei Fu, Yongxin Yang, Tim Hospedales, Tao Xiang, Shaogang Gong
2015 arXiv   pre-print
vectors; (2) a novel zero-shot learning algorithm for multi-label data that exploits the unique compositionality property of semantic word vector representations; and (3) a transductive learning strategy  ...  In this paper, for the first time, we investigate and formalise a general framework for multi-label zero-shot learning, addressing the unique challenge therein: how to exploit multi-label correlation at  ...  Hence we propose two more principled multi-label zero-shot algorithms -Direct Multi-label zero-shot Prediction (DMP) and Transductive Multi-label zero-shot Prediction(TraMP).  ... 
arXiv:1503.07790v1 fatcat:btznqtfc45bo5n6qsj5qhqjiee

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.  ...  Some results are shown in Tab. 1 and Fig. 1 Transductive multi-label zero-shot learning Many real-world data are intrinsically multi-label.  ... 
arXiv:1503.07884v1 fatcat:or4zahtjj5atpoxks5n4dilega

Transductive Multi-label Zero-shot Learning

Yanwei Fu, Yongxin Yang, Tim Hospedales, Tao Xiang, Shaogang Gong
2014 Proceedings of the British Machine Vision Conference 2014   unpublished
Multi-Label Zero-Shot Framework In this paper, we propose a novel framework for multi-label zero-shot learning.  ...  With this synthetic dataset, we are able to propose two new multi-label algorithms -direct multi-label zero-shot prediction (DMP) and transductive multi-label zero-shot prediction (TraMP).  ...  Multi-Label Zero-Shot Framework In this paper, we propose a novel framework for multi-label zero-shot learning.  ... 
doi:10.5244/c.28.7 fatcat:njsvwzdshneznbu3luxyn2jm2e

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.  ...  We call this problem the projection domain shift problem and propose a novel framework, transductive multi-view embedding, to solve it.  ...  Recognition by Multi-view Bayesian Label Propagation We now introduce a unified framework for exploiting unlabelled target data transductively to improve zero-shot recognition as well as N-shot learning  ... 
doi:10.1007/978-3-319-10605-2_38 fatcat:clv6flbs4najfoxbhyfucgsxhy

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 Zero-Shot Hashing for Multi-Label Image Retrieval [article]

Qin Zou, Zheng Zhang, Ling Cao, Long Chen, Song Wang
2019 arXiv   pre-print
In this paper, for the first time, a novel transductive zero-shot hashing method is proposed for multi-label unseen image retrieval.  ...  However, existing zeor-shot hashing methods focus on the retrieval of single-label images, and cannot handle multi-label images.  ...  TRANSDUCTIVE MULTI-LABEL ZERO-SHOT HASHING A.  ... 
arXiv:1911.07192v1 fatcat:mr5kdlsi5faxpn2a2obakha3se

Learning Robust Visual-Semantic Embeddings [article]

Yao-Hung Hubert Tsai and Liang-Kang Huang and Ruslan Salakhutdinov
2017 arXiv   pre-print
to transductive settings.  ...  We evaluate our method on Animals with Attributes and Caltech-UCSD Birds 200-2011 dataset with a wide range of applications, including zero and few-shot image recognition and retrieval, from inductive  ...  From Zero to Few-Shot Learning In this subsection, we extend our experiments from transductive zero-shot to transductive few-shot learning.  ... 
arXiv:1703.05908v2 fatcat:bmvr3bbvavepbg7k7gwgks7gne

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.  ...  CCS CONCEPTS • Computing methodologies → Machine learning approaches; Multi-task learning; Classification and regression trees.  ...  in some classes (i.e., zero shot).  ... 
doi:10.1145/3485447.3512033 fatcat:o4jes64ec5hhfhoffrxx57j5fa

A Simple Exponential Family Framework for Zero-Shot Learning [chapter]

Vinay Kumar Verma, Piyush Rai
2017 Lecture Notes in Computer Science  
Moreover, it extends seamlessly to few-shot learning by easily updating these distributions when provided with a small number of additional labelled examples from unseen classes.  ...  Unlike most existing methods for zero-shot learning that represent classes as fixed embeddings in some vector space, our generative model naturally represents each class as a probability distribution.  ...  We conduct our experiments on various problem settings, including standard inductive zero-shot learning (only using seen class labeled examples), transductive zero-shot learning (using seen class labeled  ... 
doi:10.1007/978-3-319-71246-8_48 fatcat:5dnfdwh53rgwfo3ewbpx5k6r5m

A Generative Approach to Zero-Shot and Few-Shot Action Recognition [article]

Ashish Mishra, Vinay Kumar Verma, M Shiva Krishna Reddy, Arulkumar S, Piyush Rai, Anurag Mittal
2018 arXiv   pre-print
) and generalized zero-shot learning settings.  ...  We present a generative framework for zero-shot action recognition where some of the possible action classes do not occur in the training data.  ...  They have also introduced a multi-task visual-semantic mapping for zero-shot action recognition.  ... 
arXiv:1801.09086v1 fatcat:m5pdvxu57fd47or3lraqdlnsze

Transductive Zero-Shot Hashing via Coarse-to-Fine Similarity Mining [article]

Hanjiang Lai, Yan Pan
2017 arXiv   pre-print
Zero-shot Hashing (ZSH) is to learn hashing models for novel/target classes without training data, which is an important and challenging problem.  ...  In this paper, we study the transductive ZSH, i.e., we have unlabeled data for novel classes.  ...  Transductive Zero-Shot Hashing In this section, we describe an architecture of deep convolution network designed for transductive zero-shot hashing (TZSH).  ... 
arXiv:1711.02856v1 fatcat:eqwut2d64fay7bindfcu6zoi7y

A Simple Exponential Family Framework for Zero-Shot Learning [article]

Vinay Kumar Verma, Piyush Rai
2018 arXiv   pre-print
Moreover, it extends seamlessly to few-shot learning by easily updating these distributions when provided with a small number of additional labelled examples from unseen classes.  ...  Unlike most existing methods for zero-shot learning that represent classes as fixed embeddings in some vector space, our generative model naturally represents each class as a probability distribution.  ...  We conduct our experiments on various problem settings, including standard inductive zero-shot learning (only using seen class labeled examples), transductive zero-shot learning (using seen class labeled  ... 
arXiv:1707.08040v3 fatcat:nnqeulrokvefxepkskddt26dra

Learning Class-Transductive Intent Representations for Zero-shot Intent Detection [article]

Qingyi Si, Yuanxin Liu, Peng Fu, Zheng Lin, Jiangnan Li, Weiping Wang
2021 arXiv   pre-print
To address this problem, we propose a novel framework that utilizes unseen class labels to learn Class-Transductive Intent Representations (CTIR).  ...  Zero-shot intent detection (ZSID) aims to deal with the continuously emerging intents without annotated training data.  ...  Class-transductive Zero-shot Learning Classtransductive zero-shot learning utilizes semantic information (typically a textual description) about the unseen classes in the training stage.  ... 
arXiv:2012.01721v2 fatcat:n7zkbx72xnbbbdiceunyg3v52y

F-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning

Yongqin Xian, Saurabh Sharma, Bernt Schiele, Zeynep Akata
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we tackle any-shot learning problems i.e. zero-shot and few-shot, in a unified feature generating framework that operates in both inductive and transductive learning settings.  ...  CUB, SUN, AWA and ImageNet, and establish a new state-of-the-art in any-shot learning, i.e. inductive and transductive (generalized) zeroand few-shot learning settings.  ...  (Generalized) Zero-shot Learning We validate our model on five widely-used datasets for zero-shot learning, i.e.  ... 
doi:10.1109/cvpr.2019.01052 dblp:conf/cvpr/XianSSA19 fatcat:ri2rdtqoqbc7vnwipzixyaqwoy

Transductive Zero-Shot Learning for 3D Point Cloud Classification [article]

Ali Cheraghian, Shafin Rahman, Dylan Campbell, Lars Petersson
2019 arXiv   pre-print
This paper extends, for the first time, transductive Zero-Shot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL) approaches to the domain of 3D point cloud classification.  ...  Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification.  ...  Related Work Zero-Shot Learning: For the ZSL task, there has been significant progress, including on image recognition [35, 65, 2, 4, 29, 21, 57] , multi-label ZSL [22, 34] , and zero-shot detection  ... 
arXiv:1912.07161v2 fatcat:xmcm3vtmwnhorezswj3evyxatm
« Previous Showing results 1 — 15 out of 1,333 results