High-dimensional signature compression for large-scale image classification
The DOI matches its Crossref record; 33 of the 34 references it cites were found in a registry or an index.
Abstract
We address image classification on a large-scale, i.e. when a large number of images and classes are involved. First, we study classification accuracy as a function of the image signature dimensionality and the training set size. We show experimentally that the larger the training set, the higher the impact of the dimensionality on the accuracy. In other words, high-dimensional signatures are important to obtain state-of-the-art results on large datasets. Second, we tackle the problem of data compression on very large signatures (on the order of 105dimensions) using two lossy compression strategies: a dimensionality reduction technique known as the hash kernel and an encoding technique based on product quantizers. We explain how the gain in storage can be traded against a loss in accuracy and/or an increase in CPU cost. We report results on two large databases - ImageNet and a dataset of lM Flickr images - showing that we can reduce the storage of our signatures by a factor 64 to 128 with little loss in accuracy. Integrating the decompression in the classifier learning yields an efficient and scalable training algorithm. On ILSVRC2010 we report a 74.3% accuracy at top-5, which corresponds to a 2.5% absolute improvement with respect to the state-of-the-art. On a subset of 10K classes of ImageNet we report a top-1 accuracy of 16.7%, a relative improvement of 160% with respect to the state-of-the-art.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“since then the best published results are 45.7% and 25.7% with an approach that averages the predictions of two classifiers trained on Fisher Vectors (FVs) computed from two types of densely sampled features.29”
From ImageNet classification with deep convolutional neural networks (2017) · cites this paper as [29]
Citations
Cites
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 · cited 1×
“org) consists of more than 12M images of 17K concepts [7] and Flickr contains thousands of groups (www.”
BackgroundBeyond 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 · cited 1×
“[15], one can split an image into several regions, compute one FV per region and concatenate the per-region FVs.”
BackgroundLocality-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 2×
“Maji and Berg [18] and Wang et al. [31] then proposed efficient algorithms to learn IKSVMs.”
ResultProduct 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 · cited 3×
“[13] proposed product quantizers (PQ) for NN-search of SIFT vectors.”
BackgroundMethodLinear spatial pyramid matching using sparse coding for image classification
Yang, J., Yu, K., Gong, Y., & Huang, T. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206757 · Cited by 2,828 · cited 1×
“Yang et al. [36], Wang et al. [32] and Boureau et al. [4] showed that replacing the average pooling stage in the BOV computation by a max-pooling yielded excellent results.”
ResultWeiss, Y., Torralba, A. B., & Fergus, R. (2008) · neural information processing systems · Cited by 2,767
Aggregating local descriptors into a compact image representation
Jegou, H., Douze, M., Schmid, C., & Perez, P. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5540039 · Cited by 2,692 · cited 3×
“For instance, [23] requires dense projections and [34, 5, 14] require a global PCA.”
BackgroundMethodImproving the Fisher Kernel for Large-Scale Image Classification
Perronnin, F., Sánchez, J., & Mensink, T. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_11 · Cited by 2,588 · cited 15×
“As shown in [22], square-rooting and L2-normalizing the FV can greatly enhance the classification accuracy.”
BackgroundMethodInfluentialSelf-citationZhang, J., Marszałek, M., Lazebnik, S., & Schmid, C. (2007) · International Journal of Computer Vision · doi:10.1007/s11263-006-9794-4 · Cited by 1,923 · cited 1×
“The winners of the PASCAL VOC 2007 [8] and 2008 [9] competitions used a similar paradigm: many types of low-level local features are extracted (referred to as “channels”), one bag-of-visual-words (BOV) histogram is computed for each channel and non-linear kernel classifiers such as SVMs are used to perform classificat…”
MethodEvaluating Color Descriptors for Object and Scene Recognition
van de Sande, K. E. A., Gevers, T., & Snoek, C. G. M. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.154 · Cited by 1,783 · cited 1×
“The winners of the PASCAL VOC 2007 [8] and 2008 [9] competitions used a similar paradigm: many types of low-level local features are extracted (referred to as “channels”), one bag-of-visual-words (BOV) histogram is computed for each channel and non-linear kernel classifiers such as SVMs are used to perform classificat…”
Method
Research works printed but not linked: 6
- shi, 2009, Hash kernels, AISTATS
- bottou, 0, SGD
- berg, 2010, ILSVRC
- gong, 2009, Image classification using Gaussian mixture and local coordinate coding, PASCAL VOC 2009 Workshop
- everingham, 0, The PASCAL VOC 2008 Results
- everingham, 2007, The PASCAL VOC
Cited by
Items 201–272 of 272
Personal Documents Identification System Development Using Neural Network
Popereshnyak, S., Suprun, O., Suprun, O., & Wieckowski, T. W. (2018) · IEEE International Conference on Computer Sciences and Information Technologies (CSIT) · doi:10.1109/stc-csit.2018.8526757 · Cited by 2
Improved Deep Hashing with Scalable Interblock for Tourist Image Retrieval
Feng, J., & Sun, W. (2021) · Scientific Programming · doi:10.1155/2021/9937061 · Cited by 2
“Due to the fast query speed and low storage cost, learning-based hash has been attracting research interests and was applied to applications such as large-scale object retrieval [4], image classification [5], and detection [3].”
MethodMalware family classification via efficient Huffman features
O’Shaughnessy, S., & Breitinger, F. (2021) · Forensic Science International Digital Investigation · doi:10.1016/j.fsidi.2021.301192 · Cited by 2
Compressive image retrieval with modified images
Zhang, C., & Akashi, T. (2015) · Asian Control Conference (ASCC) · doi:10.1109/ascc.2015.7244465 · Cited by 2
“[19] shows satisfactory classification results with Hash Kernel (HK) compression method on large-scale databases.”
MethodImage Retrieval Using Eigen Queries
Raval, N., Tonge, R., & Jawahar, C. V. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37444-9_36 · Cited by 2
“Even though in many cases p << d, there exist some compact codes [1, 28, 29] which represent an image with very few dimensions.”
BackgroundHuang, M., Mu, Z., & Zeng, H. (2015) · Cited by 2
Прогноз состояния объекта на основе применения фильтра Калмана и глубоких нейронных сетей
Пучков, А. Ю., A.Yu., P., Dli, M. I., Ивановна, Л. Е., Лобанева, Е. И., Vasilkova, M. A., & Vasilkova, M. A. (2019) · Международный журнал Программные продукты и системы · doi:10.15827/0236-235x.127.368-376 · Cited by 2
Automatic Classification of Galaxies Based on SVM
Bastanfard, A., Amirkhani, D., & abbasiasl, M. (2019) · International Conference on Computer and Knowledge Engineering · doi:10.1109/iccke48569.2019.8965020 · Cited by 2
“They compared their results with the Spars coding method, which was implemented in [17], and compared the way the average Fisher vectors were calculated on the SIFT properties and implemented in [18].”
MethodSupervised discrete hashing through similarity learning
Wang, H., Liu, X., & Nie, X. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-08799-5 · Cited by 3
“As for deep hashing models, in [23], a novel supervised deep hashing model (DSH) was proposed to perform simultaneous feature representation learning and hash code learning using pairwise labels.”
MethodNooka, S. P. (2016) · RIT Scholar Works (Rochester Institute of Technology) · Cited by 2
Faster Binary Embeddings for Preserving Euclidean DistancesPreprint
Zhang, J., & Saab, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.00712 · Cited by 5
“Although the above random projection G and binary embedding f achieve optimal bit complexity up to constants, it has been observed in practice that the length of the binary sequence m is usually around O(n) to guarantee reasonable accuracy [12, 31, 34].”
BackgroundHashing-Based Efficient Outfit Recommendation
Guan, W., Song, X., Zhou, D., & Nie, L. (2025) · Synthesis lectures on information concepts, retrieval, and services · doi:10.1007/978-3-031-81048-0_6 · Cited by 2
Kayacı, N., Kiremitler, N. B., Deneme, İ., Kalay, M., Ozbasaran, A., Zorlu, Y., Önses, M. S., & Usta, H. (2025) · Advanced Materials · doi:10.1002/adma.202506067 · Cited by 1
Gupta, T. (2025) · International Conference on Smart and Intelligent Systems (SISCON) · doi:10.1109/siscon66686.2025.11409295 · Cited by 7
“Our network achieves state-of-the-art performance, substantially outperforming previous approaches [13], [14].”
InfluentialOffline 1000-Class Classification on a Smartphone
Kawano, Y., & Yanai, . (2014) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2014.35 · Cited by 1
“The basic processing flow is the same as the state-of-theart large-scale image recognition [8] and real-time mobile image recognition [4].”
BackgroundHierarchical Spherical Hashing for Compressing High Dimensional Vectors
Bondugula, S., & Davis, L. S. (2015) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2015.80 · Cited by 1
Boosted kernel for image categorization
Lechervy, A., Gosselin, P.-H., & Precioso, F. (2013) · Multimedia Tools and Applications · doi:10.1007/s11042-012-1328-1 · Cited by 3
Sparse discriminative Fisher vectors in visual classification
Garg, V., Chandra, S., & Jawahar, C. V. (2012) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/2425333.2425388 · Cited by 2
“A recent work [22] describes a strategy that uses the Product Quantization codes itself in classi.cation.”
BackgroundMethodInfluentialHierarchical Learning for Large-Scale Image Classification via CNN and Maximum Confidence Path
Lu, C. H., Qu, Y., Shi, C., Jianping Fan, B., Wu, Y., & Wang, H. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24078-7_23 · Cited by 1
Advancing Iterative Quantization Hashing Using Isotropic Prior
Li, L., Liu, G., & Liu, Q. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-27674-8_16 · Cited by 1
Smart Sampling and Optimal Dimensionality Reduction of Big Data Using Compressed Sensing
Maronidis, A., Chatzilari, E., Nikolopoulos, S., & Kompatsiaris, I. Y. (2016) · Studies in big data · doi:10.1007/978-3-319-30265-2_12 · Cited by 1
Accelerating Convolutional Neural Networks Using Fine-Tuned Backpropagation Progress
Li, Y., Chen, Z., Cai, Y., Huang, D., & Li, Q. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-55705-2_20 · Cited by 1
Large Scale Visual Classification with Parallel, Imbalanced Bagging of Incremental LIBLINEAR SVM
Doan, T.-N., Do, T. N., & Poulet, F. (2013) · HAL · Cited by 1
Large Scale Image Retrieval and Its Challenges
Azim, T., & Ahmed, S. (2018) · SpringerBriefs in computer science · doi:10.1007/978-3-319-98524-4_4 · Cited by 1
An algorithm for indentation image classification and detection based on deep learning
Shilin, C., & Wei, S. (2021) · Measurement Sensors · doi:10.1016/j.measen.2021.100100 · Cited by 1
Number Plate Recognition System Using Convolutional Neural Network
Arora, P., Kapse, V. M., Sinha, S., & Gera, S. (2021) · International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO) · doi:10.1109/icrito51393.2021.9596134 · Cited by 1
Large Scale Metric Learning for Distance-Based Image Classification on Open Ended Data Sets
Mensink, T., Verbeek, J. J., Perronnin, F., & Csurka, G. (2013) · Advances in computer vision and pattern recognition · doi:10.1007/978-1-4471-5520-1_9 · Cited by 2
Self-citationResearch on cigarette defect detection based on deep learning
Liu, L., Zhang, W., Li, Y., & Shi, S. (2024) · International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) · doi:10.1109/aiea62095.2024.10692965 · Cited by 1
“Then, through random gradient descent, the error is continuously adjusted and the parameters are optimized to achieve the best performance of the network model [16].”
MethodFast Binary Embedding for High-Dimensional Data
Yu, F. X., Gong, Y., & Kumar, S. (2015) · Springer eBooks · doi:10.1007/978-3-319-14998-1_16 · Cited by 1
“Taking image retrieval and classification as an example, it has been shown recently that in order to achieve high accuracy on large-scale datasets, it is advantageous to use very high-dimensional descriptors such as Fisher Vectors (FV) [27, 26, 31], Vector of Locally Aggregated Descriptors (VLAD) [15], Locally Constra…”
BackgroundMethodInfluentialLarge Scale Visual Classification with Many Classes
Doan, T.-N., Do, T., & Poulet, F. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39712-7_48 · Cited by 3
Efficient representation for image recognition
Zhang, Y. (2015) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/63616 · Cited by 1
“the Gaussian mixture model (GMM) parameters, which usually uses the mean and variance parts [63]: ∂G ∂μj = 1 n √ wj n ∑”
BackgroundMethodInfluentialComputational Models of Machine Vision - Goal, Role and Success
Azim, T. (2014) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0004737601790186 · Cited by 1
Heisterklaus, I., Patel, G. K., & Bulla, C. (2015) · International symposium on image and signal processing and analysis/ISPA ... · doi:10.1109/ispa.2015.7306029
“There are lots of possibilities to reduce the memory requirements of an application using Fisher Vectors, e.g binarization [5], [2] and product quantization [6].”
Efficient binary codes for extremely high-dimensional data
Lin, T., & Liu, T.-L. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025448
Cartesian Genetic Programmingを用いた特徴量の階層的な低次元化に基づく画像分類
航太, 齊., & 智晴, 長. (2015) · doi:10.11394/tjpnsec.6.55
Implicit Sparse Code HashingPreprint
Lin, T., Ke, T.-W., & Liu, T.-L. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1512.00130 · Cited by 1
“In [26], Sánchez and Perronnin demonstrate that FV is effective for large-scale classification problems and report significant improvements over then state-of-the-art on ILSVRC 2010 [2].”
BackgroundLarge scale multi-class classification using latent classifiers
Mai, T.-D., Ngo, T. D., Le, D.-D., Duong, D. A., Hoàng, K. V., & Satoh, S. (2015) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2015.7340800
“For example, considering the tree T32,2, the classification accuracy of our method is 20.15% meanwhile of the method proposed by Bengio et al. [7] and Deng et al. [8] is 7.22% and 11.9%, respectively.”
MethodInfluentialAction Localization with Approximately
Oneaţă, D., Verbeek, J. J., & Schmid, C. (2014)
Approximation of the Gradient of the Error Probability for Vector Quantizers.
Diamantini, C., Genga, L., & Potena, D. (2012) · TU/e Research Portal
Low-bit representation of linear classifier weights for mobile large-scale image classification
Kawano, Y., & Yanai, . (2015) · Asian Conference on Pattern Recognition · doi:10.1109/acpr.2015.7486551
“However, it will bring severe performance reduction [8].”
BackgroundMethodNon-linear distance based large scale data classifications
Al-Behadili, H., Grumpe, A., Dopp, C., & Wöhler, C. (2015) · IEEE International Conference on Progress in Informatics and Computing · doi:10.1109/pic.2015.7489921 · Cited by 1
Simple tag-based subclass representations for visually-varied image classes
Li, X., Xu, P., Shi, Y., Larson, M., & Hanjalić, A. (2016) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2016.7500265
“For large-scale image tagging tasks, the most popular model based image tagging method is to train a binary classifier for each tag [16], [12], [14].”
Method3.Compact Binary Hashing for Efficient Large-scale Image Retrieval
Irie, G. (2015) · The Journal of The Institute of Image Information and Television Engineers · doi:10.3169/itej.69.124
feature extraction, encoding and classication for action recognition
Kantorov, V., & Laptev, I. (2014)
2.Machine Learning for Visual Recognition
Harada, T. (2015) · The Journal of The Institute of Image Information and Television Engineers · doi:10.3169/itej.69.117
Boosted Deep Neural Network with Weighted Output Layers
Hua, C. (2017) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2017-01-1997
Margin-Based Sample Filtering for Image Classification Using Convolutional Neural Networks
Kaplanoglou, P. I., & Diamantaras, K. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451592 · Cited by 1
“The AlexNet model achieved ∼ 15% top-5 error which was a considerable improvement compared to the state of the art at that time [3] which achieved ∼ 26% Top-5 error.”
Robot Machine Vision by Deep Machine Learning
Lu, H. (2019) · DEStech Transactions on Computer Science and Engineering · doi:10.12783/dtcse/iteee2019/28812
6. Extracting Local Invariant Features Using Orientation Maps
Ichimura, N. (2012) · The Journal of The Institute of Image Information and Television Engineers · doi:10.3169/itej.66.831
Al-Sharkawy, A. A., Bahgat, G. A., Hemayed, E. E., & Mashali, S. A. (2020) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-7998-6690-9.ch016
Platform-specific model compression for deep neural networks with joint methods
Lin, S. (2020) · Digital Repository Service (Northeastern University) · doi:10.17760/d20398267
A Latent Variable Augmentation Method for Image Categorization with Insufficient Training Samples
Lin, L., Zheng, X. W., Liu, B., Chen, W., & Xiao, Y. (2021) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3451165
Scientific Applications of Machine Learning Algorithms
(2022) · Advances in systems analysis, software engineering, and high performance computing book series · doi:10.4018/978-1-7998-8350-0.ch004
Ding, C. (2019) · Digital Repository Service (Northeastern University) · doi:10.17760/d20323953
Guan, W., Song, X., Chang, X., & Nie, L. (2022) · Synthesis lectures on information concepts, retrieval, and services · doi:10.1007/978-3-031-18817-6_7
Melanoma (Skin Cancer) Classifier Using RESNet
Naveen, K., Uday, B. K., & Tejaswi, T. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-19-5191-6_7
Deep Learning for Computer Vision in Smart Cities
García-Retuerta, D. (2022) · Gredos (University of Salamanca) · doi:10.14201/gredos.150948 · Cited by 1
Decentralized Ledger Technology-enabled Textile Fabric Flaw Detection SystemPreprint
Karthick, V., Jawahar Vishnu, B., & Jishnu Barath, C. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4816482
Dropout and Its Role in Neural Networking
Mukherji, S., Tomar, S. S., Nigam, S., Sonker, S. K., & Kumar, S. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5955-5_9
Fourure, D. (2017) · theses.fr (ABES) · doi:10.70675/b54dd90bz6e92z43fez8df3z313ad61607ea · Cited by 1
du Terrail, J. O. (2018) · theses.fr (ABES) · doi:10.70675/083d206az0a4ez4480z866ez53e9de431d15 · Cited by 1
Robust detection of astronomical sources using convolutional neural networks
Paillassa, M. (2020) · theses.fr (ABES) · doi:10.70675/eadcd5fdz3c39z4c82z9901z314800455d3d · Cited by 1
Inference acceleration and optimization in deep neural networks for computer vision
Keddous, F. E. (2022) · theses.fr (ABES) · doi:10.70675/b08b2f98z66c2z46d7za694z241b7296cbd2
Sparsity and phase collapse in deep convolutional networks
Zarka, J. (2022) · theses.fr (ABES) · doi:10.70675/4349d1b1z1f33z4ae2z9c0bza72efb3287fd
Methodology and tooling for energy-efficient neural networks computation and optimization
Waltsburger, H. (2024) · theses.fr (ABES) · doi:10.70675/6aadb508z47bfz4dc6z95b6zbd5a77514a0a
Learning discriminative representations to interpret image recognition models
Figueroa, F. T. (2024) · theses.fr (ABES) · doi:10.70675/b1004b04z42a5z4eb1z9006z898e627b47c5
Segmentation by deep learning with geometric constraints and active contours
Makaroff, N. (2024) · theses.fr (ABES) · doi:10.70675/861dcf2ez2d8az413fz8c00zb51af12facad
Maier, A., Christlein, V., Breininger, K., Würfl, T., Unberath, M., & Rieß, C. (2026) · doi:10.1515/9783111386690-021
Artificial Intelligence for the Eye
Antony, B. J., & Mareels, I. (2026) · Springer eBooks · doi:10.1007/978-3-032-11023-7_7
Chat-Fusion: An Efficient Batch Inference System for Cloud LLMs Serving
Yu, J., Wang, L., Wang, M., Li, H., Han, Y., Li, X., Li, H., Zhang, K., & Wang, Y. (2026) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2026.3734339
“Locality sensitive hashing (LSH): [28], [29], [30], [31], [32], [33], [34] is an effective method for clustering vectors in high-dimensional spaces.”
Metadata
- Authors
- Sanchez, J., & Perronnin, F.
- Affiliations
- Xerox (France) (FR)
- Venue
- CVPR 2011
- Publisher
- IEEE
- Published
- 2011-06
- Pages
- 1665-1672
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2053229256
- Semantic Scholar
- eefcc7bcc05436dac9881acb4ff4e4a0b730e175
- Cited by
- 272
- References
- 34
- Citations by year
- 2026: 3 · 2025: 5 · 2024: 7 · 2023: 6 · 2022: 11 · 2021: 19 · 2020: 10 · 2019: 23 · 2018: 17 · 2017: 23 · 2016: 21 · 2015: 46 · 2014: 30 · 2013: 30 · 2012: 18
- FWCI
- 19.28
- 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)
- 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 classification, large-scale image classification, signature compression, lossy compression, dimensionality reduction, training data size, storage efficiency, scalable training, ImageNet, Flickr images
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.