Small codes and large image databases for recognition
Abstract
The Internet contains billions of images, freely available online. Methods for efficiently searching this incredibly rich resource are vital for a large number of applications. These include object recognition, computer graphics, personal photo collections, online image search tools. In this paper, our goal is to develop efficient image search and scene matching techniques that are not only fast, but also require very little memory, enabling their use on standard hardware or even on handheld devices. Our approach uses recently developed machine learning techniques to convert the Gist descriptor (a real valued vector that describes orientation energies at different scales and orientations within an image) to a compact binary code, with a few hundred bits per image. Using our scheme, it is possible to perform real-time searches with millions from the Internet using a single large PC and obtain recognition results comparable to the full descriptor. Using our codes on high quality labeled images from the LabelMe database gives surprisingly powerful recognition results using simple nearest neighbor techniques.
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
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Low dimensional encoding enables training models with global characteristics and yields better generalisation power for the underlying anatomy.
“Low dimensional encoding enables us to train models with global characteristics but also yields better generalisation power for the underlying anatomy as shown in earlier work [43].”
From Anatomically constrained neural networks (ACNNS): application to cardiac image enhancement and segmentation (2018) · cites this paper as [43]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
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 · see citing works
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472 · see citing works
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 · see citing works
Near-Optimal Hashing Algorithms for Approximate Nearest Neighbor in High Dimensions
Andoni, A., & Indyk, P. (2006) · 2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06) · doi:10.1109/focs.2006.49 · Cited by 1,067 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Shin, H.-C., Roth, H. R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2528162 · Cited by 5,759 · see citing works
Product Quantization for Nearest Neighbor Search
Jégou, H., Douze, M., & Schmid, C. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.57 · Cited by 2,956 · see citing works
Aggregating Local Image Descriptors into Compact Codes
Jegou, H., Perronnin, F., Douze, M., Sanchez, J., Perez, P., & Schmid, C. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.235 · Cited by 1,503 · see citing works
Oktay, O., Ferrante, E., Kamnitsas, K., Heinrich, M., Bai, W., Caballero, J., Cook, S. A., de Marvao, A., Dawes, T., O'Regan, D. P., et al. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2017.2743464 · Cited by 751 · see citing works
“Low dimensional encoding enables us to train models with global characteristics but also yields better generalisation power for the underlying anatomy as shown in earlier work [37].”
BackgroundThe use of machine learning algorithms in recommender systems: a systematic review
Portugal, I., Alencar, P., & Cowan, D. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.12.020 · Cited by 743 · see citing works
“…is a plethora of ML algorithms (k-nearest neighbor [48], clustering [28], Bayes network [22], to name a few types), which are used in applications that range from vacuum cleaner robots [13] and assistance for disabled people [30] to pattern recognition in images [63], or self-driving vehicles [62].”
BackgroundLDAHash: Improved Matching with Smaller Descriptors
Strecha, C., Bronstein, A. M., Bronstein, M. M., & Fua, P. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.103 · Cited by 605 · see citing works
Deep hashing for compact binary codes learning
Liong, V. E., Lu, J., Wang, G., Moulin, P., & Zhou, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298862 · Cited by 545 · see citing works
Multiple feature hashing for real-time large scale near-duplicate video retrieval
Song, J., Yang, Y., Huang, Z., Shen, H. T., & Hong, R. (2011) · Proceedings of the 19th ACM international conference on Multimedia · doi:10.1145/2072298.2072354 · Cited by 334 · see citing works
[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 · see citing works
High-dimensional signature compression for large-scale image classification
Sanchez, J., & Perronnin, F. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995504 · Cited by 272 · see citing works
Grauman, K., & Leibe, B. (2011) · Synthesis Lectures on Artificial Intelligence and Machine Learning · doi:10.2200/s00332ed1v01y201103aim011 · Cited by 126 · see citing works
- Authors
- Torralba, A., Fergus, R., & Weiss, Y.
- Affiliations
- Massachusetts Institute of Technology (US)
- New York University (US)
- Hebrew University of Jerusalem (IL)
- Venue
- 2008 IEEE Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2008-06
- Pages
- 1-8
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2154956324
- Cited by
- 727
- References
- 4
- Citations by year
- 2026: 2 · 2025: 3 · 2024: 5 · 2023: 10 · 2022: 13 · 2021: 16 · 2020: 21 · 2019: 25 · 2018: 32 · 2017: 72 · 2016: 71 · 2015: 85 · 2014: 77 · 2013: 60 · 2012: 69
- FWCI
- 44.32
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- Funders
- National Science Foundation
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- image search, GIST descriptors, compact binary codes, image retrieval, scene matching, nearest neighbor search, real-time search, memory-efficient indexing, object recognition, LabelMe, handheld devices
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
