String representations and distances in deep Convolutional Neural Networks for image classification
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Recent advances in image classification mostly rely on the use of powerful local features combined with an adapted image representation. Although Convolutional Neural Network (CNN) features learned from ImageNet were shown to be generic and very efficient, they still lack of flexibility to take into account variations in the spatial layout of visual elements. In this paper, we investigate the use of structural representations on top of pretrained CNN features to improve image classification. Images are represented as strings of CNN features. Similarities between such representations are computed using two new edit distance variants adapted to the image classification domain. Our algorithms have been implemented and tested on several challenging datasets, 15Scenes, Caltech101, Pascal VOC 2007 and MIT indoor. The results show that our idea of using structural string representations and distances clearly improves the classification performance over standard approaches based on CNN and SVM with linear kernel, as well as other recognized methods of the literature. HighlightsA structural representation of images on top of CNN features is proposed.Images are represented as strings to integrate spatial relationships.We introduce tailored string edit distances to compare images represented as strings.Experiments show that our structural approach is more powerful than existing ones.It also outperforms state-of-the-art CNN-based classification methods.
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
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
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10578-9_23 · Cited by 3,034
Fei-Fei, L., Fergus, R., & Perona, P. (2007) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2005.09.012 · Cited by 2,359
The 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 1×
“Other grid configurations have been proposed combining for instance 1 × 1 , 3 × 1 (three horizontal lines), 2 × 2 divisions [19, 20, 21].”
Method
Cited by
Handcrafted vs. non-handcrafted features for computer vision classification
Nanni, L., Ghidoni, S., & Brahnam, S. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.05.025 · Cited by 542
Lu, C., Wang, Z., & Zhou, B. (2017) · Advanced Engineering Informatics · doi:10.1016/j.aei.2017.02.005 · Cited by 434
“In the image recognition field, normally each convolution kernel denotes a type of feature, such as oriented edges or corners; thus, salient features in the whole image would be identified using convolution computation [36].”
BackgroundTidriri, K., Chatti, N., Verron, S., & Tiplica, T. (2016) · Annual Reviews in Control · doi:10.1016/j.arcontrol.2016.09.008 · Cited by 397
Learning Affective Features With a Hybrid Deep Model for Audio–Visual Emotion Recognition
Zhang, S., Zhang, S., Huang, T., Gao, W., & Tian, Q. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2719043 · Cited by 346
“Due to the large-scale available training data and the effective training strategies introduced in recent works, CNNs have exhibited significant success in various vision tasks like object detection and recognition [29]–[32].”
BackgroundConvolutional Recurrent Neural Networks forHyperspectral Data Classification
Wu, H., & Prasad, S. (2017) · Remote Sensing · doi:10.3390/rs9030298 · Cited by 268
Metadata
- Authors
- Barat, C., & Ducottet, C.
- Venue
- Pattern Recognition
- Publisher
- Elsevier BV
- Published
- 2016-06
- Volume
- 54
- Pages
- 104-115
- ISSN
- 0031-3203 (ISSN-L)
- OpenAlex
- W2332352554
- Cited by
- 61
- References
- 5
- FWCI
- 8.90
- 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.