The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Exploiting local features from deep networks for image retrieval
Abstract
Deep convolutional neural networks have been successfully applied to image classification tasks. When these same networks have been applied to image retrieval, the assumption has been made that the last layers would give the best performance, as they do in classification. We show that for instance-level image retrieval, lower layers often perform better than the last layers in convolutional neural networks. We present an approach for extracting convolutional features from different layers of the networks, and adopt VLAD encoding to encode features into a single vector for each image. We investigate the effect of different layers and scales of input images on the performance of convolutional features using the recent deep networks OxfordNet and GoogLeNet. Experiments demonstrate that intermediate layers or higher layers with finer scales produce better results for image retrieval, compared to the last layer. When using compressed 128-D VLAD descriptors, our method obtains state-of-the-art results and outperforms other VLAD and CNN based approaches on two out of three test datasets. Our work provides guidance for transferring deep networks trained on image classification to image retrieval tasks.
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
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
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
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
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077
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 1×
“Traditional image retrieval approaches rely on hand-crafted features like SIFT descriptors, which are usually encoded into bag-of-words (BoW) histograms [30].”
MethodCNN Features Off-the-Shelf: An Astounding Baseline for Recognition
Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2014.131 · Cited by 4,451
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019 · cited 1×
“As a universal image representation, CNN features can be applied to other recognition tasks and perform well [19, 6, 34].”
BackgroundLearning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.222 · Cited by 3,150
Object retrieval with large vocabularies and fast spatial matching
Philbin, J., Chum, O., Isard, M., Sivic, J., & Zisserman, A. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383172 · Cited by 2,929
Cited by
Large-Scale Image Retrieval with Attentive Deep Local Features
Noh, H., Araujo, A., Sim, J., Weyand, T., & Han, B. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.374 · Cited by 847
Deep Image Retrieval: Learning Global Representations for Image Search
Gordo, A., Almazán, J., Revaud, J., & Larlus, D. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46466-4_15 · Cited by 787
SIFT Meets CNN: A Decade Survey of Instance Retrieval
Zheng, L., Yang, Y., & Tian, Q. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2709749 · Cited by 752
Yang, F., Choi, W., & Lin, Y. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.234 · Cited by 608
Self-citationPatternNet: A benchmark dataset for performance evaluation of remote sensing image retrieval
Zhou, W., Newsam, S., Li, C., & Shao, Z. (2018) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2018.01.004 · Cited by 571
Automatic classification of defective photovoltaic module cells in electroluminescence images
Deitsch, S., Christlein, V., Berger, S., Buerhop-Lutz, C., Maier, A., Gallwitz, F., & Riess, C. (2019) · Solar Energy · doi:10.1016/j.solener.2019.02.067 · Cited by 558
End-to-End Learning of Deep Visual Representations for Image Retrieval
Gordo, A., Almazán, J., Revaud, J., & Larlus, D. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-017-1016-8 · Cited by 537
A Decade Survey of Content Based Image Retrieval Using Deep Learning
Dubey, S. R. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3080920 · Cited by 356
Chaos-Based Image Encryption: Review, Application, and Challenges
Zhang, B., & Liu, L. (2023) · Mathematics · doi:10.3390/math11112585 · Cited by 328
“Although some excellent image retrieval schemes have been proposed in [193,194], they are all calculated for plaintext features, and their protection of image information is limited.”
BackgroundSupervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks
Yang, H.-F., Lin, K., & Chen, C.-S. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2666812 · Cited by 314
[Paper] Visual Instance Retrieval with Deep Convolutional Networks
Razavian, A. S., Sullivan, J., Carlsson, S., & Maki, A. (2016) · ITE Transactions on Media Technology and Applications · doi:10.3169/mta.4.251 · Cited by 276
Food Recognition: A New Dataset, Experiments, and Results
Ciocca, G., Napoletano, P., & Schettini, R. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2016.2636441 · Cited by 266
Near-Duplicate Video Retrieval by Aggregating Intermediate CNN Layers
Kordopatis-Zilos, G., Papadopoulos, S., Patras, I., & Kompatsiaris, Y. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-51811-4_21 · Cited by 83
Liu, Y., Xu, K., & Wang, D. (2018) · Metals · doi:10.3390/met8030197 · Cited by 39
Video Copy Detection Using Spatio-Temporal CNN Features
Zhou, Z., Chen, J., Yang, C.-N., & Sun, X. (2019) · IEEE Access · doi:10.1109/access.2019.2930173 · Cited by 18
Image Security Retrieval Based on Chaotic Algorithm and Deep Learning
Zhang, Q., Yan, Y., Lin, Y., & Li, Y. (2022) · IEEE Access · doi:10.1109/access.2022.3185421 · Cited by 9
“Using intermediate layers to capture the local patterns of objects is better than using the output of the last layer for image retrieval [15].”
Background
Metadata
- Authors
- Ng, J. Y.-H., Yang, F., & Davis, L. S.
- Venue
- 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
- Publisher
- IEEE
- Published
- 2015-06
- Pages
- 53-61
- OpenAlex
- W1922773808
- Cited by
- 344
- References
- 35
- FWCI
- 19.67
- Type
- conference paper
- 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.