Good Practice in Large-Scale Learning for Image Classification
Open accessThe DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
We benchmark several SVM objective functions for large-scale image classification. We consider one-versus-rest, multiclass, ranking, and weighted approximate ranking SVMs. A comparison of online and batch methods for optimizing the objectives shows that online methods perform as well as batch methods in terms of classification accuracy, but with a significant gain in training speed. Using stochastic gradient descent, we can scale the training to millions of images and thousands of classes. Our experimental evaluation shows that ranking-based algorithms do not outperform the one-versus-rest strategy when a large number of training examples are used. Furthermore, the gap in accuracy between the different algorithms shrinks as the dimension of the features increases. We also show that learning through cross-validation the optimal rebalancing of positive and negative examples can result in a significant improvement for the one-versus-rest strategy. Finally, early stopping can be used as an effective regularization strategy when training with online algorithms. Following these "good practices," we were able to improve the state of the art on a large subset of 10K classes and 9M images of ImageNet from 16.7 percent Top-1 accuracy to 19.1 percent.
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: 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
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Lazebnik, S., Schmid, C., & Ponce, J. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.68 · Cited by 7,916
Self-citationVideo Google: a text retrieval approach to object matching in videos
Sivic, & Zisserman (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238663 · Cited by 6,367 · cited 1×
“The Bag-of-Visual-Words (BOV), which describes an image as a histogram of quantized local descriptors [69], [18], has been the most popular image representation for image classification.”
BackgroundLabelMe: A Database and Web-Based Tool for Image Annotation
Russell, B. C., Torralba, A., Murphy, K. P., & Freeman, W. T. (2008) · International Journal of Computer Vision · doi:10.1007/s11263-007-0090-8 · Cited by 4,210
Locality-constrained Linear Coding for image classification
Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., & Gong, Y. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5540018 · Cited by 3,100 · cited 2×
“Hence, efficient alternatives have been sought such as Locality-constrained Linear Coding (LLC) [81], [48] which performs a local embedding of the descriptors.”
MethodProduct Quantization for Nearest Neighbor Search
Jégou, H., Douze, M., & Schmid, C. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.57 · Cited by 2,956 · cited 2×
“Coding techniques such as product quantization (PQ) [35] have also been used to compress the data [66], [60], [78].”
MethodSelf-citationSolving Multiclass Learning Problems via Error-Correcting Output Codes
Dietterich, T. G., & Bakiri, G. (1995) · Journal of Artificial Intelligence Research · doi:10.1613/jair.105 · Cited by 2,739
Improving the Fisher Kernel for Large-Scale Image Classification
Perronnin, F., Sánchez, J., & Mensink, T. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_11 · Cited by 2,588 · cited 1×
“Standard large-scale image classification pipelines use high-dimensional image descriptors in combination with linear classifiers [48], [66].”
Self-citationWhat is the best multi-stage architecture for object recognition?
Jarrett, K., Kavukcuoglu, K., Ranzato, M. A., & LeCun, Y. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459469 · Cited by 2,153
Cited by
Multi-scale Orderless Pooling of Deep Convolutional Activation Features
Gong, Y., Wang, L., Guo, R., & Lazebnik, S. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10584-0_26 · Cited by 1,030
Incremental on-line learning: A review and comparison of state of the art algorithms
Losing, V., Hammer, B., & Wersing, H. (2018) · Neurocomputing · doi:10.1016/j.neucom.2017.06.084 · Cited by 382
Learning Visual Features from Large Weakly Supervised Data
Joulin, A., van der Maaten, L., Jabri, A., & Vasilache, N. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46478-7_5 · Cited by 302
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
A learning-based multimodel integrated framework for dynamic traffic flow forecasting
Zhou, T., Han, G., Xu, X., Han, C., Huang, Y., & Qin, J. (2019) · Neural Processing Letters · doi:10.1007/s11063-018-9804-x · Cited by 66
Metadata
- Authors
- Akata, Z., Perronnin, F., Harchaoui, Z., & Schmid, C.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2014-03
- Volume
- 36
- Issue
- 3
- Pages
- 507-520
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- OpenAlex
- W2120725344
- Cited by
- 158
- References
- 16
- FWCI
- 23.05
- Type
- journal article
- 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.