The DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Is Second-Order Information Helpful for Large-Scale Visual Recognition?
Open accessAbstract
By stacking layers of convolution and nonlinearity, convolutional networks (ConvNets) effectively learn from lowlevel to high-level features and discriminative representations. Since the end goal of large-scale recognition is to delineate complex boundaries of thousands of classes, adequate exploration of feature distributions is important for realizing full potentials of ConvNets. However, state-of-the-art works concentrate only on deeper or wider architecture design, while rarely exploring feature statistics higher than first-order. We take a step towards addressing this problem. Our method consists in covariance pooling, instead of the most commonly used first-order pooling, of highlevel convolutional features. The main challenges involved are robust covariance estimation given a small sample of large-dimensional features and usage of the manifold structure of covariance matrices. To address these challenges, we present a Matrix Power Normalized Covariance (MPNCOV) method. We develop forward and backward propagation formulas regarding the nonlinear matrix functions such that MPN-COV can be trained end-to-end. In addition, we analyze both qualitatively and quantitatively its advantage over the well-known Log-Euclidean metric. On the ImageNet 2012 validation set, by combining MPN-COV we achieve over 4%, 3% and 2.5% gains for AlexNet, VGG-M and VGG-16, respectively; integration of MPN-COV into 50-layer ResNet outperforms ResNet-101 and is comparable to ResNet-152. The source code will be available on the project page: http://www.peihuali.org/MPN-COV.
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
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
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
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
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
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839
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
A Multilinear Singular Value Decomposition
De Lathauwer, L., De Moor, B., & Vandewalle, J. (2000) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/s0895479896305696 · Cited by 4,106
Return of the Devil in the Details: Delving Deep into Convolutional Nets
Chatfield, K., Simonyan, K., Vedaldi, A., & Zisserman, A. (2014) · Proceedings of the British Machine Vision Conference 2014 · doi:10.5244/c.28.6 · Cited by 3,335
A well-conditioned estimator for large-dimensional covariance matrices
Ledoit, O., & Wolf, M. (2004) · Journal of Multivariate Analysis · doi:10.1016/s0047-259x(03)00096-4 · Cited by 3,046 · cited 6×
“Our MPN-COV closely conforms to the shrinkage principle [28, 18], i.”
BackgroundMethodInfluentialMatConvNet: Convolutional Neural Networks for MATLAB
Vedaldi, A., & Lenc, K. (2015) · Proceedings of the 23rd ACM international conference on Multimedia · doi:10.1145/2733373.2807412 · Cited by 2,444
Bilinear CNN Models for Fine-Grained Visual Recognition
Lin, T.-Y., RoyChowdhury, A., & Maji, S. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.170 · Cited by 2,135
A Riemannian Framework for Tensor Computing
Pennec, X., Fillard, P., & Ayache, N. (2006) · International Journal of Computer Vision · doi:10.1007/s11263-005-3222-z · Cited by 1,550
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
(2014) · arXiv (Cornell University) · Cited by 942
Geometric Means in a Novel Vector Space Structure on Symmetric Positive‐Definite Matrices
Arsigny, V., Fillard, P., Pennec, X., & Ayache, N. (2007) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/050637996 · Cited by 819
Deep filter banks for texture recognition and segmentation
Cimpoi, M., Maji, S., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299007 · Cited by 646
Shrinkage Algorithms for MMSE Covariance Estimation
Chen, Y., Wiesel, A., Eldar, Y. C., & Hero, A. O. (2010) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2010.2053029 · Cited by 567
Semantic Segmentation with Second-Order Pooling
Carreira, J., Caseiro, R., Batista, J., & Sminchisescu, C. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33786-4_32 · Cited by 458
Non-Euclidean statistics for covariance matrices, with applications to diffusion tensor imaging
Dryden, I. L., Koloydenko, A., & Zhou, D. (2009) · The Annals of Applied Statistics · doi:10.1214/09-aoas249 · Cited by 383
Matrix Backpropagation for Deep Networks with Structured Layers
Ionescu, C., Vantzos, O., & Sminchisescu, C. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.339 · Cited by 281
Higher-Order Occurrence Pooling for Bags-of-Words: Visual Concept Detection
Koniusz, P., Yan, F., Gosselin, P.-H., & Mikolajczyk, K. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2545667 · Cited by 117
Training Deep Networks with Structured Layers by Matrix BackpropagationPreprint
Ionescu, C., Vantzos, O., & Sminchisescu, C. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1509.07838 · Cited by 102
Local Log-Euclidean Multivariate Gaussian Descriptor and Its Application to Image Classification
Li, P., Wang, Q., Zeng, H., & Zhang, L. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2560816 · Cited by 80
Self-citationWang, Q., Li, P., Zuo, W., & Zhang, L. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.480 · Cited by 60
Self-citationFrom dictionary of visual words to subspaces: Locality-constrained affine subspace coding
Li, P., Lu, X., & Wang, Q. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298848 · Cited by 42
Self-citationHigher-Order Pooling of CNN Features via Kernel Linearization for Action Recognition
Cherian, A., Koniusz, P., & Gould, S. J. (2017) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2017.22 · Cited by 41
Elementary Estimators for Sparse Covariance Matrices and other Structured Moments
Yang, E., Lozano, A. C., & Ravikumar, P. (2014) · Cited by 19
Zhou, D., Dryden, I. L., Koloydenko, A. A., Audenaert, K. M. R., & Bai, L. (2015) · Journal of Applied Statistics · doi:10.1080/02664763.2015.1080671 · Cited by 19
Cited by
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., & Hu, Q. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01155 · Cited by 9,641
Self-citationSecond-Order Attention Network for Single Image Super-Resolution
Dai, T., Cai, J., Zhang, Y., Xia, S.-T., & Zhang, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01132 · Cited by 2,010
Review of Image Classification Algorithms Based on Convolutional Neural Networks
Chen, L., Li, S., Bai, Q., Yang, J., Jiang, S., & Miao, Y. (2021) · Remote Sensing · doi:10.3390/rs13224712 · Cited by 789
Global Second-Order Pooling Convolutional Networks
Gao, Z., Xie, J., Wang, Q., & Li, P. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00314 · Cited by 524
Self-citationFine-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
Metadata
- Authors
- Li, P., Xie, J., Wang, Q., & Zuo, W.
- Venue
- 2017 IEEE International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2017-10
- Pages
- 2089-2097
- OpenAlex
- W2601789736
- Cited by
- 294
- References
- 32
- FWCI
- 8.17
- 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.