Towards good practice in large-scale learning for image classification
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
We propose a benchmark of several objective functions for large-scale image classification: we compare the one-vs-rest, multiclass, ranking and weighted average ranking SVMs. Using stochastic gradient descent optimization, we can scale the learning to millions of images and thousands of classes. Our experimental evaluation shows that ranking based algorithms do not outperform a one-vs-rest strategy and that the gap between the different algorithms reduces in case of high-dimensional data. We also show that for one-vs-rest, learning through cross-validation the optimal degree of imbalance between the positive and the negative samples can have a significant impact. Furthermore, early stopping can be used as an effective regularization strategy when training with stochastic gradient algorithms. Following these "good practices", we were able to improve the state-of-the-art on a large subset of 10K classes and 9M of images of lmageNet from 16.7% accuracy to 19.1%.
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
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 1×
“In the literature several high dimensional descriptors exist, e.g ., the Fisher vector [24, 26], local coordinate cod-∗ ing [37] and supervector coding [42].”
BackgroundProduct 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 1×
“For FV we employ product quantization [15] and for BOV scalar quantization [11].”
MethodSelf-citationImproving 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 2×
“, the Fisher vector [24, 26], local coordinate cod-”
BackgroundMethodSelf-citationThe devil is in the details: an evaluation of recent feature encoding methods
Chatfield, K., Lempitsky, V., Vedaldi, A., & Zisserman, A. (2011) · Procedings of the British Machine Vision Conference 2011 · doi:10.5244/c.25.76 · Cited by 834 · cited 3×
“A detailed comparison of these high-dimensional descriptors was performed in [9]; it showed that the Fisher vector representation outperforms the others.”
BackgroundMethodInfluentialHigh-dimensional signature compression for large-scale image classification
Sanchez, J., & Perronnin, F. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995504 · Cited by 272 · cited 12×
“Large-scale image classification has recently received significant interest [11, 19, 28, 29].”
BackgroundMethodInfluentialSelf-citation
Cited by
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
“…Sande, Amir Habibian, Cees G. M. Snoek (Sanchez and Perronnin, 2011; Scheirer et al., 2012) XRCE 27.1 - Xerox Research Centre Europe†, LEAR INRIA ‡ Florent Perronnin†, Zeynep Akata†‡, Zaid Harchaoui‡, Cordelia Schmid‡ (Perronnin et al., 2012) Table 5 Teams participating in ILSVRC2010-2012,…”
BackgroundInfluentialImage 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
“Given the size of these datasets, at each pass of the SGD routine we sample all positives but only a random subset of negatives (Perronnin et al, 2012, S ´ anchez and Perronnin, 2011).”
InfluentialSelf-citationReferItGame: Referring to Objects in Photographs of Natural Scenes
Kazemzadeh, S., Ordonez, V., Matten, M., & Berg, T. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1086 · Cited by 1,048
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
Label-Embedding for Image Classification
Akata, Z., Perronnin, F., Harchaoui, Z., & Schmid, C. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2487986 · Cited by 770
Self-citation
Metadata
- Authors
- Perronnin, F., Akata, Z., Harchaoui, Z., & Schmid, C.
- Venue
- 2012 IEEE Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2012-06
- Pages
- 3482-3489
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2127279985
- Cited by
- 101
- References
- 7
- FWCI
- 16.41
- 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.