Transductive Multi-View Zero-Shot Learning
Open accessThe DOI matches its Crossref record; 72 of the 74 references it cites were found in a registry or an index.
Abstract
Most existing zero-shot learning approaches exploit transfer learning via an intermediate semantic representation shared between an annotated auxiliary dataset and a target dataset with different classes and no annotation. A projection from a low-level feature space to the semantic representation space is learned from the auxiliary dataset and applied without adaptation to the target dataset. In this paper we identify two inherent limitations with these approaches. First, due to having disjoint and potentially unrelated classes, the projection functions learned from the auxiliary dataset/domain are biased when applied directly to the target dataset/domain. We call this problem the projection domain shift problem and propose a novel framework, transductive multi-view embedding, to solve it. The second limitation is the prototype sparsity problem which refers to the fact that for each target class, only a single prototype is available for zero-shot learning given a semantic representation. To overcome this problem, a novel heterogeneous multi-view hypergraph label propagation method is formulated for zero-shot learning in the transductive embedding space. It effectively exploits the complementary information offered by different semantic representations and takes advantage of the manifold structures of multiple representation spaces in a coherent manner. We demonstrate through extensive experiments that the proposed approach (1) rectifies the projection shift between the auxiliary and target domains, (2) exploits the complementarity of multiple semantic representations, (3) significantly outperforms existing methods for both zero-shot and N-shot recognition on three image and video benchmark datasets, and (4) enables novel cross-view annotation tasks.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“What is interesting to see here is that Overfeat > Decaf since both are based on the same Convolutional Neural Network (CNN) model of [32].”
BackgroundCollective dynamics of ‘small-world’ networks
Watts, D. J., & Strogatz, S. H. (1998) · Nature · doi:10.1038/30918 · Cited by 43,060
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918 · cited 1×
“However, this does not effectively exploit the multi-view complementarity, and suffers from labelled data (prototype) sparsity.”
Background(2008) · Journal of Machine Learning Research · Cited by 33,051
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387
Learning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 9,239 · cited 1×
“The advantages of heterogeneous hypergraphs We argue that the pairwise similarity of heterogeneous hypergraph is a distributed representation [3].”
BackgroundRecognition-by-components: A theory of human image understanding.
Biederman, I. (1987) · Psychological Review · doi:10.1037/0033-295x.94.2.115 · Cited by 5,621 · cited 1×
“Humans can distinguish 30,000 basic object classes [3] and many more subordinate ones (e.g. breeds of dogs).”
BackgroundLearning Deep Architectures for AI
Bengio, Y. (2009) · now publishers, Inc. eBooks · doi:10.1561/9781601982957 · Cited by 4,941
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019 · cited 1×
“In addition, the Decaf (D) [10] feature is also considered for AwA.”
BackgroundLearning with Local and Global Consistency
Zhou, D., Bousquet, O., Lal, T. N., Weston, J., & Schölkopf, B. (2003) · MPG.PuRe (Max Planck Society) · Cited by 3,864
Semi-Supervised Learning Literature Survey
Zhu, X. (2005) · Minds at UW (University of Wisconsin) · Cited by 3,844
Caltech-UCSD Birds-200-2011 Dataset
Wah, C. (2024) · CaltechAUTHORS (California Institute of Technology) · doi:10.57702/i9oeewf6 · Cited by 3,525
Return of the Devil in the Details: Delving Deep into Convolutional Nets
Chatfield, K., Simonyan, K., Vedaldi, A., & Zisserman, A. (2014) · Proceedings of the British Machine Vision Conference 2014 · doi:10.5244/c.28.6 · Cited by 3,335
Canonical Correlation Analysis: An Overview with Application to Learning Methods
Hardoon, D. R., Szedmak, S., & Shawe-Taylor, J. (2004) · Neural Computation · doi:10.1162/0899766042321814 · Cited by 3,202 · cited 1×
“Thus, with our framework, we can now infer attributes for any test instance via the learned embedding space Γ as ˆ y Au .”
Method(1992) · doi:10.5555/176313.176316 · Cited by 2,892
Adapting visual category models to new domains
Saenko, K., Kulis, B., Fritz, M., & Darrell, T. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_16 · Cited by 2,847
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6229 · Cited by 2,680
Small worlds: the dynamics of networks between order and randomness
(2000) · Choice Reviews Online · doi:10.5860/choice.37-5722 · Cited by 2,360
DeViSE: A Deep Visual-Semantic Embedding Model
Frome, A., Corrado, G. S., Shlens, J., Samy Bengio, A., Dean, J., Ranzato, M., & Mikolov, T. (2013) · Cited by 2,308
Describing objects by their attributes
Farhadi, A., Endres, I., Hoiem, D., & Forsyth, D. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206772 · Cited by 1,917 · cited 2×
“Different from the multi-view hypergraphs proposed in [19] which are homogeneous, that is, constructed in each view independently, we construct a multi-view heterogeneous hypergraph: using the nodes from one view as query nodes to compute hyperedges in another view.”
BackgroundLearning to detect unseen object classes by between-class attribute transfer
Lampert, C. H., Nickisch, H., & Harmeling, S. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206594 · Cited by 1,849 · cited 7×
“Common semantic representations include binary vectors of visual attributes [27], [31], [15] (e.g. ’hasTail’ in Fig.”
BackgroundMethodInfluentialIntroduction to Semi-Supervised Learning
Zhu, X., & Goldberg, A. B. (2009) · Synthesis Lectures on Artificial Intelligence and Machine Learning · doi:10.1007/978-3-031-01548-9 · Cited by 1,766
Attribute-Based Classification for Zero-Shot Visual Object Categorization
Lampert, C. H., Nickisch, H., & Harmeling, S. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.140 · Cited by 1,627
Learning to detect unseen object classes by between-class attribute transfer
Lampert, C. H., Nickisch, H., & Harmeling, S. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvprw.2009.5206594 · Cited by 1,528
Unsupervised Visual Domain Adaptation Using Subspace Alignment
Fernando, B., Habrard, A., Sebban, M., & Tuytelaars, T. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.368 · Cited by 1,314 · cited 1×
“This process alleviates the projection domain shift problem, as well as providing a common space in which heterogeneous views can be directly compared, and their complementarity exploited (Sec.”
BackgroundOverview and Recent Advances in Partial Least Squares
Rosipal, R., & Krämer, N. (2006) · Lecture Notes in Computer Science · doi:10.1007/11752790_2 · Cited by 1,091 · cited 1×
“This discrepancy is caused when the projections learned from the 40 auxiliary classes are applied directly to project the Pig instances – what ‘hasTail’ (as well as the other 84 attributes) visually means is different now.”
BackgroundZero-Shot Learning Through Cross-Modal Transfer
Socher, R., Ganjoo, M., Sridhar, H., Bastani, O., Manning, C. D., & Ng, A. Y. (2013) · arXiv · doi:10.48550/arxiv.1301.3666 · Cited by 997 · cited 5×
“Without any labelled data for the target classes, exter-nal knowledge is needed to represent what each target class looks like, in the form of class prototypes.”
BackgroundMethodInfluentialCollective dynamics of 'small-world' networks
Watts, D. J., & Strogatz, S. H. (2011) · The Structure and Dynamics of Networks · doi:10.1515/9781400841356.301 · Cited by 988
Parikh, D., & Grauman, K. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126281 · Cited by 851 · cited 1×
“X S ∈ R n s × t and X T ∈ R n T × t denote the t − dimensional low-level feature vectors of auxiliary and target instances respectively. z S and z T are the auxiliary and target class label vectors.”
BackgroundZero-Shot Learning with Semantic Output Codes
Palatucci, M., Pomerleau, D., Hinton, G. E., et al. (2018) · Figshare · doi:10.1184/r1/6476456.v1 · Cited by 816 · cited 1×
“X S ∈ R n s × t and X T ∈ R n T × t denote the t − dimensional low-level feature vectors of auxiliary and target instances respectively. z S and z T are the auxiliary and target class label vectors.”
BackgroundClustering on the Unit Hypersphere using von Mises-Fisher Distributions
Banerjee, A., Dhillon, I. S., Ghosh, J., & Sra, S. (2005) · MPG.PuRe (Max Planck Society) · doi:10.5555/1046920.1088718 · Cited by 766
Zero-Shot Learning with Semantic Output Codes
Palatucci, M., Pomerleau, D., Hinton, G. E., & Mitchell, T. M. (2018) · Figshare · doi:10.1184/r1/6476456 · Cited by 752
Return of the Devil in the Details: Delving Deep into Convolutional NetsPreprint
Chatfield, K., Simonyan, K., Vedaldi, A., et al. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1405.3531 · Cited by 663 · cited 1×
“The zero-shot learning results of each individual space are indicated as It is widely reported that deep features have better performance than ‘hand-crafted’ features on many computer vision benchmark datasets [5], [42].”
BackgroundLabel-Embedding for Attribute-Based Classification
Akata, Z., Perronnin, F., Harchaoui, Z., & Schmid, C. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.111 · Cited by 618 · cited 4×
“They can be roughly categorised according to the semantic representation(s) used: DAP and IAP ([27], [28]), M2LATM [15], ALE [1], [36] and [50] use attributes only; HLE/AHLE [1] and Mo/Ma/O/D [38] use both attributes and linguistic knowledge bases (same as us); [54] uses attribute and some…”
BackgroundMethodInfluentialRecognizing human actions by attributes
Liu, J., Kuipers, B., & Savarese, S. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995353 · Cited by 563 · cited 3×
“X S ∈ R n s × t and X T ∈ R n T × t denote the t − dimensional low-level feature vectors of auxiliary and target instances respectively. z S and z T are the auxiliary and target class label vectors.”
BackgroundA Multi-View Embedding Space for Modeling Internet Images, Tags, and Their Semantics
Gong, Y., Ke, Q., Isard, M., & Lazebnik, S. (2014) · International Journal of Computer Vision · doi:10.1007/s11263-013-0658-4 · Cited by 540
Spectral clustering and transductive learning with multiple views
Zhou, D., & Burges, C. J. C. (2007) · Proceedings of the 24th international conference on Machine learning · doi:10.1145/1273496.1273642 · Cited by 437
NEIL: Extracting Visual Knowledge from Web Data
Chen, X., Shrivastava, A., & Gupta, A. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.178 · Cited by 408
Covariate Shift by Kernel Mean Matching
Gretton, A., Smola, A., Huang, J., Schmittfull, M., Borgwardt, K., & Schölkopf, B. (2008) · Dataset Shift in Machine Learning · doi:10.7551/mitpress/9780262170055.003.0008 · Cited by 378
Evaluating knowledge transfer and zero-shot learning in a large-scale setting
Rohrbach, M., Stark, M., & Schiele, B. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995627 · Cited by 303 · cited 2×
“Note that for the auxiliary dataset, Y iS is given as each data point is labelled.”
BackgroundMethodImage retrieval via probabilistic hypergraph ranking
Huang, Y., Liu, Q., Zhang, S., & Metaxas, D. N. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5540012 · Cited by 293
What helps where – and why? Semantic relatedness for knowledge transfer
Rohrbach, M., Stark, M., Szarvas, G., Gurevych, I., & Schiele, B. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5540121 · Cited by 273 · cited 1×
“Note that for the auxiliary dataset, Y iS is given as each data point is labelled.”
BackgroundHypergraph spectral learning for multi-label classification
Sun, L., Ji, S., & Ye, J. (2008) · Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1401890.1401971 · Cited by 258 · cited 2×
“Interestingly, our way of defining hyperedges naturally corresponds to the star expansion [46] where the query node (i.e. ψ ik ) is introduced to connect each node in the hyperedge e ij where In the embedding space Γ , similarity sets ∆ ij can be compared.”
BackgroundMethodDomain Transfer SVM for video concept detection
Duan, L., Tsang, I. W., Xu, D., & Maybank, S. J. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206747 · Cited by 255 · cited 1×
“This process alleviates the projection domain shift problem, as well as providing a common space in which heterogeneous views can be directly compared, and their complementarity exploited (Sec.”
BackgroundLearning Coupled Feature Spaces for Cross-Modal Matching
Wang, K., He, R., Wang, W., Wang, L., & Tan, T. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.261 · Cited by 235 · cited 1×
“Recognition could now be achieved using NN classification with the embedded prototypes/N-shots as labelled data.”
MethodTransductive Multi-view Embedding for Zero-Shot Recognition and Annotation
Fu, Y., Hospedales, T. M., Xiang, T., Fu, Z., & Gong, S. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10605-2_38 · Cited by 224 · cited 5×
“The same Bayesian model averaging [14] can be used here to estimate these prior probabilities.”
BackgroundMethodResultInfluentialSelf-citationSocher, R., & Fei-Fei, L. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5540112 · Cited by 217
Transfer Learning in a Transductive Setting
Rohrbach, M., Ebert, S., & Schiele, B. (2013) · MPG.PuRe (Max Planck Society) · Cited by 212
]Video object segmentation by hypergraph cut
Huang, Y., Liu, Q., & Metaxas, D. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206795 · Cited by 209
Describing objects by their attributes
Farhadi, A., Endres, I., Hoiem, D., & Forsyth, D. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvprw.2009.5206772 · Cited by 208
Contextual Hypergraph Modeling for Salient Object Detection
Li, X., Li, Y., Shen, C., Dick, A., & Hengel, A. V. D. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.413 · Cited by 205
Designing Category-Level Attributes for Discriminative Visual Recognition
Yu, F. X., Cao, L., Feris, R. S., Smith, J. R., & Chang, S.-F. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.105 · Cited by 195 · cited 1×
“X S ∈ R n s × t and X T ∈ R n T × t denote the t − dimensional low-level feature vectors of auxiliary and target instances respectively. z S and z T are the auxiliary and target class label vectors.”
BackgroundMulti-View Video Summarization
Fu, Y., Guo, Y., Zhu, Y., Liu, F., Song, C., & Zhou, Z.-H. (2010) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2010.2052025 · Cited by 194
Self-citationMulti-view Regression Via Canonical Correlation Analysis
Kakade, S. M., & Foster, D. P. (2007) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-72927-3_8 · Cited by 184
Multi-attribute spaces: Calibration for attribute fusion and similarity search
Scheirer, W. J., Kumar, N., Belhumeur, P. N., & Boult, T. E. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248021 · Cited by 169 · cited 1×
“X S ∈ R n s × t and X T ∈ R n T × t denote the t − dimensional low-level feature vectors of auxiliary and target instances respectively. z S and z T are the auxiliary and target class label vectors.”
BackgroundLearning Multimodal Latent Attributes
Fu, Y., Hospedales, T. M., Xiang, T., & Gong, S. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.128 · Cited by 142
Self-citationA PAC-Bayesian bound for Lifelong LearningPreprint
Pentina, A., & Lampert, C. H. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1311.2838 · Cited by 140 · cited 1×
“Inspired by humans’ ability to recognise without seeing samples, and motivated by the prohibitive cost of training sample collection and annotation, the research area of learning to learn or lifelong learning [35], [6] has received increasing interests.”
BackgroundKernel Methods in Computer Vision
Lampert, C. H. (2009) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000027 · Cited by 133 · cited 1×
“d the subsequent computation more robust. Specifically, we extend zeroscore normalisation to the similarity sets: (a) We assume 4. Most previous work [36], [56] sets $ by cross-validation. Inspired by [26], a simpler strategy for setting $is adopted: t median k;l=1; ;n i k ; j l > 2 in order to have roughly the same…”
MethodLearning the Relative Importance of Objects from Tagged Images for Retrieval and Cross-Modal Search
Hwang, S. J., & Grauman, K. L. (2011) · International Journal of Computer Vision · doi:10.1007/s11263-011-0494-3 · Cited by 128
Sharing features between objects and their attributes
Hwang, S. J., Sha, F., & Grauman, K. L. (2011) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2011.5995543 · Cited by 117 · cited 1×
“X S ∈ R n s × t and X T ∈ R n T × t denote the t − dimensional low-level feature vectors of auxiliary and target instances respectively. z S and z T are the auxiliary and target class label vectors.”
BackgroundAttribute Learning for Understanding Unstructured Social Activity
Fu, Y., Hospedales, T. M., Xiang, T., & Gong, S. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33765-9_38 · Cited by 108 · cited 1×
“In this case a word space is extracted from linguistic knowledge bases e.g., Wikipedia by natural language processing models such as [4], [32].”
MethodSelf-citationMixture Regression for Covariate Shift
Storkey, A., & Sugiyama, M. (2007) · The MIT Press eBooks · doi:10.7551/mitpress/7503.003.0172 · Cited by 106
Domain Transfer SVM for video concept detection
Duan, L., Tsang, I. W.-H., Xu, D., & Maybank, S. J. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvprw.2009.5206747 · Cited by 91
A Unified Probabilistic Approach Modeling Relationships between Attributes and Objects
Wang, X., & Ji, Q. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.264 · Cited by 61 · cited 1×
“They can be roughly categorised according to the semantic representation(s) used: DAP and IAP ([27], [28]), M2LATM [15], ALE [1], [36] and [50] use attributes only; HLE/AHLE [1] and Mo/Ma/O/D [38] use both attributes and linguistic knowledge bases (same as us); [54] uses attribute and some…”
MethodContext-Aware Hypergraph Construction for Robust Spectral Clustering
Li, X., Hu, W., Shen, C., Dick, A., & Zhang, Z. M. (2013) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2013.126 · Cited by 59
Fujiwara, Y., & Irie, G. (2014) · Cited by 49
Multi-view hypergraph learning by patch alignment framework
Hong, C., Yu, J., Li, J., & Chen, X. (2013) · Neurocomputing · doi:10.1016/j.neucom.2013.02.017 · Cited by 31
Kernel Methods in Computer Vision
Lampert, C. H. (2007) · now publishers, Inc. eBooks · doi:10.1561/9781601982698 · Cited by 13
Learning Tags from Unsegmented Videos of Multiple Human Actions
Hospedales, T. M., Gong, S., & Xiang, T. (2011) · Proceedings · doi:10.1109/icdm.2011.90 · Cited by 12 · cited 1×
“Leveraging this cross-view mapping, annotation [24], [60], [20] can be improved and applied in novel ways.”
Self-citationContextual Hypergraph Modelling for Salient Object DetectionPreprint
Li, X., Li, Y., Shen, C., Dick, A., & van den Hengel, A. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1310.5767 · Cited by 11
Translating topics to words for image annotation
Wang, Y., & Gong, S. (2007) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/1321440.1321594 · Cited by 9 · cited 1×
“Similarly, we have three views of each unlabelled instance f A ( X T ) , f V ( X T ) and X T .”
BackgroundSelf-citationA Multi-View Embedding Space for Modeling Internet Images, Tags, and their SemanticsPreprint
Gong, Y., Ke, Q., Isard, M., et al. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1212.4522 · Cited by 4
Research works printed but not linked: 2
- rosch, 1977, Classification of real-world objects: Origins and representations in cognition, Thinking Readings in Cognitive Science
- mikolov, 0, Efficient estimation of word representation in vector space, Proc ICLR Workshop
Cited by
Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly
Xian, Y., Lampert, C. H., Schiele, B., & Akata, Z. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2857768 · Cited by 1,678
“Apart from the inductive zero-shot learning set-up where the model has no access to neither visual nor side-information of unseen classes, transductive zero-shot learning approaches [28], [44], [45], [46], [47], [48], [49] use visual or semantic information of both seen and unseen classes without having access to the…”
BackgroundFeature Generating Networks for Zero-Shot Learning
Xian, Y., Lorenz, T., Schiele, B., & Akata, Z. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00581 · Cited by 1,080
Semantic Autoencoder for Zero-Shot Learning
Kodirov, E., Xiang, T., & Gong, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.473 · Cited by 921
“Existing ZSL models mostly suffer from the projection domain shift problem [21].”
BackgroundSelf-citationInteractive medical image segmentation using deep learning with image-specific fine tuning
Wang, G., Li, W., Zuluaga, M. A., Pratt, R., Patel, P. A., Aertsen, M., Doel, T., David, A. L., Deprest, J., Ourselin, S., et al. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2791721 · Cited by 843
Learning Deep Representations of Fine-Grained Visual Descriptions
Reed, S., Akata, Z., Lee, H., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.13 · Cited by 760
“TMVHLP [14] builds a hypergraph on a multiview embedding space learned via CCA which uses deep image features and attributes.”
Background
Metadata
- Authors
- Fu, Y., Hospedales, T. M., Xiang, T., & Gong, S.
- Affiliations
- Walt Disney (United States) (US)
- Queen Mary University of London (GB)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2015-11-01
- Volume
- 37
- Issue
- 11
- Pages
- 2332-2345
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- OpenAlex
- W2141350700
- Cited by
- 514
- References
- 74
- Citations by year
- 2026: 17 · 2025: 32 · 2024: 32 · 2023: 52 · 2022: 60 · 2021: 75 · 2020: 62 · 2019: 57 · 2018: 64 · 2017: 41 · 2016: 21 · 2015: 1
- FWCI
- 41.51
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Queen Mary Research Online (Queen Mary University of London) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- zero-shot learning, transductive learning, multi-view embedding, semantic representation, transfer learning, manifold structure
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.