From N to N+1: Multiclass Transfer Incremental Learning
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
Since the seminal work of Thrun [16], the learning to learn paradigm has been defined as the ability of an agent to improve its performance at each task with experience, with the number of tasks. Within the object categorization domain, the visual learning community has actively declined this paradigm in the transfer learning setting. Almost all proposed methods focus on category detection problems, addressing how to learn a new target class from few samples by leveraging over the known source. But if one thinks of learning over multiple tasks, there is a need for multiclass transfer learning algorithms able to exploit previous source knowledge when learning a new class, while at the same time optimizing their overall performance. This is an open challenge for existing transfer learning algorithms. The contribution of this paper is a discriminative method that addresses this issue, based on a Least-Squares Support Vector Machine formulation. Our approach is designed to balance between transferring to the new class and preserving what has already been learned on the source models. Extensive experiments on subsets of publicly available datasets prove the effectiveness of our approach.
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
Learning 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 3×
“Experiments on various subsets of the Caltech-256 [9] and Animals with Attributes (AwA) datasets [13] show that our algorithm outperforms the One-Versus-All (OVA) extension of [18], as well as other baselines [11, 20, 1].”
MethodDomain adaptation with structural correspondence learning
Blitzer, J., McDonald, R., & Pereira, F. (2006) · Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing - EMNLP '06 · doi:10.3115/1610075.1610094 · Cited by 1,543 · cited 1×
“Experiments are reported in Section 5, followed by conclusions in Section 6.”
MethodOn feature combination for multiclass object classification
Gehler, P., & Nowozin, S. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459169 · Cited by 797 · cited 2×
“Specifically, for the Caltech-256 experiments we used the following features: oriented and unoriented PHOG shape descriptors, SIFT appearance descriptors, region covariance and local binary patterns totalling in 14 descriptor types [8].”
Method
Cited by
iCaRL: Incremental Classifier and Representation Learning
Rebuffi, S.-A., Kolesnikov, A., Sperl, G., & Lampert, C. H. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.587 · Cited by 3,988
“[17] showed that a loss of accuracy can be avoided when adding new classes to an existing linear multi-class classifier, as long as the classifiers can be retrained from at least a small amount of data for all classes.”
BackgroundLarge Scale Incremental Learning
Wu, Y., Chen, Y., Wang, L., Ye, Y., Liu, Z., Guo, Y., & Fu, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00046 · Cited by 1,313
Recent Advances in Open Set Recognition: A Survey
Geng, C., Huang, S.-J., & Chen, S. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2981604 · Cited by 1,006
Class-Incremental Learning: A Survey
Zhou, D.-W., Wang, Q.-W., Qi, Z.-H., Ye, H.-J., Zhan, D.-C., & Liu, Z. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3429383 · Cited by 376
“However, most of them address the incremental learning within two tasks, i.e. , the model is only updated with a single new stage [12], [13].”
BackgroundMnemonics Training: Multi-Class Incremental Learning Without Forgetting
Liu, Y., Su, Y., Liu, A.-A., Schiele, B., & Sun, Q. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01226 · Cited by 309
Metadata
- Authors
- Kuzborskij, I., Orabona, F., & Caputo, B.
- Venue
- 2013 IEEE Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2013-06
- Pages
- 3358-3365
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2166344886
- Cited by
- 137
- References
- 3
- FWCI
- 5.20
- Type
- conference paper
- Language
- en
- Open access
- green
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.