Learning Deep Hierarchical Visual Feature Coding
The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
In this paper, we propose a hybrid architecture that combines the image modeling strengths of the bag of words framework with the representational power and adaptability of learning deep architectures. Local gradient-based descriptors, such as SIFT, are encoded via a hierarchical coding scheme composed of spatial aggregating restricted Boltzmann machines (RBM). For each coding layer, we regularize the RBM by encouraging representations to fit both sparse and selective distributions. Supervised fine-tuning is used to enhance the quality of the visual representation for the categorization task. We performed a thorough experimental evaluation using three image categorization data sets. The hierarchical coding scheme achieved competitive categorization accuracies of 79.7% and 86.4% on the Caltech-101 and 15-Scenes data sets, respectively. The visual representations learned are compact and the model's inference is fast, as compared with sparse coding methods. The low-level representations of descriptors that were learned using this method result in generic features that we empirically found to be transferrable between different image data sets. Further analysis reveal the significance of supervised fine-tuning when the architecture has two layers of representations as opposed to a single layer.
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 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
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 · cited 2×
“To tackle the vision problem, the convolutional neural network [15], [16] was developed.”
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
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
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
Video 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 2×
“In the last decade, bag of words (BoW) frameworks [1] have achieved good classification performances on many object and scene image data sets.”
Approximation capabilities of multilayer feedforward networks
Hornik, K. (1991) · Neural Networks · doi:10.1016/0893-6080(91)90009-t · Cited by 6,091
Emergence of simple-cell receptive field properties by learning a sparse code for natural images
Olshausen, B. A., & Field, D. J. (1996) · Nature · doi:10.1038/381607a0 · Cited by 5,694 · cited 1×
“The input reconstruction error is also used, though in a slightly different manner, in sparse dictionary learning [24], which can also be hierarchically stacked to become a deep network.”
Training Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879 · cited 2×
“(7) Hinton [53] proposed the contrastive divergence (CD) algorithm, that approximates the stationary distribution with a small finite number of sampling steps and used to update the weights by iterating over the training data w i j = ε x i z j data − −x i z j recon (8) where ε is a small learning…”
Greedy layer-wise training of deep networks
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841 · cited 3×
“When there are three or more layers exist in the architecture, it is considered to be deep [12], [13].”
Hierarchical models of object recognition in cortex
Riesenhuber, M., & Poggio, T. (1999) · Nature Neuroscience · doi:10.1038/14819 · Cited by 3,309 · cited 1×
“To model the expanded spatial dimensionality in large images, we look to convolutional neural networks [9], [15], [16] and biologically inspired models [49]–[52] for inspiration.”
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 5×
“There are various approximations that help reduce the computational costs, such as limiting the optimization to within a component of a mixture model [35], using a small dictionary for sparse coding and another for pooling [28] or incorporating locality constraints [36].”
InfluentialA Practical Guide to Training Restricted Boltzmann Machines
Hinton, G. E. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8_32 · Cited by 2,852 · cited 1×
“To avoid unnecessary sampling noise [54] and reduce the variance of the estimator [55], we employ Rao-Blackwellization [56].”
Lee, H., Grosse, R., Ranganath, R., & Ng, A. Y. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553453 · Cited by 2,412
Robust Object Recognition with Cortex-Like Mechanisms
Serre, T., Wolf, L., Bileschi, S., Riesenhuber, M., & Poggio, T. (2007) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.56 · Cited by 1,667
Fisher Kernels on Visual Vocabularies for Image Categorization
Perronnin, F., & Dance, C. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383266 · Cited by 1,641
In defense of soft-assignment coding
Liu, L., Wang, L., & Liu, X. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126534 · Cited by 443
Cited by
Gopalakrishnan, K., Khaitan, S. K., Choudhary, A., & Agrawal, A. (2017) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2017.09.110 · Cited by 955
Liu, J., Gong, M., Qin, K., & Zhang, P. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2636227 · Cited by 522
Deep learning in microscopy image analysis: a survey
Xing, F., Xie, Y., Su, H., Liu, F., & Yang, L. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2766168 · Cited by 460
Deep Neural Network for Structural Prediction and Lane Detection in Traffic Scene
Li, J., Mei, X., Prokhorov, D., & Tao, D. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2522428 · Cited by 435
Stacked Convolutional Denoising Auto-Encoders for Feature Representation
Du, B., Xiong, W., Wu, J., Zhang, L., Zhang, L., & Tao, D. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2016.2536638 · Cited by 416
Metadata
- Authors
- Goh, H., Thome, N., Cord, M., & Lim, J.-H.
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2014-12
- Volume
- 25
- Issue
- 12
- Pages
- 2212-2225
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W2063756240
- Cited by
- 105
- References
- 19
- FWCI
- 10.68
- Type
- journal article
- Language
- en
- Open access
- closed
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.