Incremental Learning of Random Forests for Large-Scale Image Classification
The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
Large image datasets such as ImageNet or open-ended photo websites like Flickr are revealing new challenges to image classification that were not apparent in smaller, fixed sets. In particular, the efficient handling of dynamically growing datasets, where not only the amount of training data but also the number of classes increases over time, is a relatively unexplored problem. In this challenging setting, we study how two variants of Random Forests (RF) perform under four strategies to incorporate new classes while avoiding to retrain the RFs from scratch. The various strategies account for different trade-offs between classification accuracy and computational efficiency. In our extensive experiments, we show that both RF variants, one based on Nearest Class Mean classifiers and the other on SVMs, outperform conventional RFs and are well suited for incrementally learning new classes. In particular, we show that RFs initially trained with just 10 classes can be extended to 1,000 classes with an acceptable loss of accuracy compared to training from the full data and with great computational savings compared to retraining for each new batch of classes.
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
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
SUN database: Large-scale scene recognition from abbey to zoo
Xiao, J., Hays, J., Ehinger, K. A., Oliva, A., & Torralba, A. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539970 · Cited by 3,283
Image Classification with the Fisher Vector: Theory and Practice
Sánchez, J., Perronnin, F., Mensink, T., & Verbeek, J. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0636-x · Cited by 1,498
Towards Open World Recognition
Bendale, A., & Boult, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298799 · Cited by 529
High-dimensional signature compression for large-scale image classification
Sanchez, J., & Perronnin, F. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995504 · Cited by 272
Incremental Learning of NCM Forests for Large-Scale Image Classification
Ristin, M., Guillaumin, M., Gall, J., & Van Gool, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.467 · Cited by 82
Self-citation
Research works printed but not linked: 33
- 10.1109/CVPR.2012.6248060 · DOI · Paper page
- 10.1109/ICCV.2007.4409053 · DOI
- 10.1109/CVPR.2011.5995368 · DOI · Paper page
- 10.1109/CVPR.2012.6248055 · DOI · Paper page
- 10.1109/CVPR.2011.5995477 · DOI · Paper page
- 10.1109/CVPR.2010.5540064 · DOI · Paper page
- 10.1109/ICCVW.2009.5457447 · DOI · Paper page
- 10.1145/347090.347107 · DOI · Paper page
- lakshminarayanan, 0, Mondrian forests: Efficient online random forests, Proc Adv Neural Inf Process Syst, 3140
- schulter, 0, Online Hough-forests, Proc Brit Mach Vis Conf, 128.1
- 10.1007/s11263-009-0275-4 · DOI · Paper page
- 10.1109/CVPR.2011.5995627 · DOI · Paper page
- 10.1007/s11263-014-0713-9 · DOI
- bengio, 0, Label embedding trees for large multi-class tasks, Proc Adv Neural Inf Process Syst, 163
- deng, 0, Hedging your bets: Optimizing accuracy-specificity trade-offs in large scale visual recognition, Proc IEEE Conf Comput Vis Pattern Recog, 3450
- 10.1109/CVPR.2006.264 · DOI · Paper page
- 10.1109/ICCV.2007.4409066 · DOI · Paper page
- 10.1109/CVPR.2011.5995441 · DOI
- 10.1109/CVPR.2012.6247757 · DOI
- deng, 0, Fast and balanced: Efficient label tree learning for large scale object recognition, Proc Adv Neural Inf Process Syst, 567
- 10.1145/3147.3165 · DOI · Paper page
- wang, 0, An incremental extremely random forest classifier for online learning and tracking, Proc 16th IEEE Int Conf Image Process, 1433
- 10.1109/CVPR.2011.5995720 · DOI · Paper page
- 10.1023/A:1018628609742 · DOI · Paper page
- 10.1109/CVPR.2013.114 · DOI
- 10.1007/978-3-319-10599-4_29 · DOI · Paper page
- 10.1109/ICCV.2011.6126228 · DOI · Paper page
- 10.1109/CVPR.2013.431 · DOI · Paper page
- 10.1109/TPAMI.2013.146 · DOI · Paper page
- 10.1109/TPAMI.2008.128 · DOI · Paper page
- 10.1109/TPAMI.2013.83 · DOI · Paper page
- 10.1007/978-3-642-15555-0_6 · DOI · Paper page
- 10.1109/CVPR.2014.107 · DOI
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
Incremental Learning of Object Detectors without Catastrophic Forgetting
Shmelkov, K., Schmid, C., & Alahari, K. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.368 · Cited by 559
Mishra, N., & Pandya, S. (2021) · IEEE Access · doi:10.1109/access.2021.3073408 · Cited by 421
Rudd, E. M., Jain, L. P., Scheirer, W. J., & Boult, T. E. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2707495 · Cited by 326
A Strategy for an Uncompromising Incremental Learner
Venkatesan, R., Venkateswara, H., Panchanathan, S., & Li, B. (2017) · arXiv · doi:10.48550/arxiv.1705.00744 · Cited by 37
Metadata
- Authors
- Ristin, M., Guillaumin, M., Gall, J., & Van Gool, L.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2016-03-01
- Volume
- 38
- Issue
- 3
- Pages
- 490-503
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W2267727210
- Cited by
- 154
- References
- 8
- FWCI
- 18.14
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Funders
- CTI project (15769.1 PFES-ES)
- DFG Emmy Noether program (GA 1927/1-1)
- DFG project (GA 1927/2-2 FOR 1505)
- Toyota
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.