The DOI matches its Crossref record.
Improved Bilinear Pooling with CNNs
Open accessAbstract
Bilinear pooling of Convolutional Neural Network (CNN) features [22, 23], and their compact variants [10], have been shown to be effective at fine-grained recognition, scene categorization, texture recognition, and visual question-answering tasks among others. The resulting representation captures second-order statistics of convolutional features in a translationally invariant manner. In this paper we investigate various ways of normalizing these statistics to improve their representation power. In particular we find that the matrix square-root normalization offers significant improvements and outperforms alternative schemes such as the matrix logarithm normalization when combined with elementwise square-root and l2 normalization. This improves the accuracy by 2-3% on a range of fine-grained recognition datasets leading to a new state of the art. We also investigate how the accuracy of matrix function computations effect network training and evaluation. In particular we compare against a technique for estimating matrix square-root gradients via solving a Lyapunov equation that is more numerically accurate than computing gradients via a Singular Value Decomposition (SVD). We find that while SVD gradients are numerically inaccurate the overall effect on the final accuracy is negligible once boundary cases are handled carefully. We present an alternative scheme for computing gradients that is faster and yet it offers improvements over the baseline model. Finally we show that the matrix square-root computed approximately using a few Newton iterations is just as accurate for the classification task but allows an order-of-magnitude faster GPU implementation compared to SVD decomposition.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Cited by
Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning
Cui, Y., Song, Y., Sun, C., Howard, A., & Belongie, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00432 · Cited by 503
Fine-Grained Image Analysis With Deep Learning: A Survey
Wei, X.-S., Song, Y.-Z., Aodha, O. M., Wu, J., Peng, Y., Tang, J., Yang, J., & Belongie, S. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3126648 · Cited by 434
Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition
Yu, C., Zhao, X., Zheng, Q., Zhang, P., & You, X. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01270-0_35 · Cited by 353
Multi-view Harmonized Bilinear Network for 3D Object Recognition
Yu, T., Meng, J., & Yuan, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00027 · Cited by 318
Li, P., Xie, J., Wang, Q., & Gao, Z. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00105 · Cited by 310
Metadata
- Authors
- Lin, T.-Y., & Maji, S.
- Venue
- Procedings of the British Machine Vision Conference 2017
- Publisher
- British Machine Vision Association
- Published
- 2017
- OpenAlex
- W2964350570
- Cited by
- 224
- References
- 0
- FWCI
- 7.77
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Improved Bilinear Pooling with CNNs. https://app.cochat.ai/papers/10.5244/c.31.117
- The paper
- Lin, T.-Y., & Maji, S. (2017). Improved Bilinear Pooling with CNNs. Procedings of the British Machine Vision Conference 2017. https://doi.org/10.5244/c.31.117
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.