Where's Wally Now? Deep Generative and Discriminative Embeddings for Novelty Detection
The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
We develop a framework for novelty detection (ND) methods relying on deep embeddings, either discriminative or generative, and also propose a novel framework for assessing their performance. While much progress was made recently in these approaches, it has been accompanied by certain limitations: most methods were tested on relatively simple problems (low resolution images / small number of classes) or involved non-public data; comparative performance has often proven inconclusive because of lacking statistical significance; and evaluation has generally been done on non-canonical problem sets of differing complexity, making apples-to-apples comparative performance evaluation difficult. This has led to a relative confusing state of affairs. We address these challenges via the following contributions: We make a proposal for a novel framework to measure the performance of novelty detection methods using a trade-space demonstrating performance (measured by ROCAUC) as a function of problem complexity. We also make several proposals to formally characterize problem complexity. We conduct experiments with problems of higher complexity (higher image resolution / number of classes). To this end we design several canonical datasets built from CIFAR-10 and ImageNet (IN-125) which we make available to perform future benchmarks for novelty detection as well as other related tasks including semantic zero/adaptive shot and unsupervised learning. Finally, we demonstrate, as one of the methods in our ND framework, a generative novelty detection method whose performance exceeds that of all recent best-in-class generative ND 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
Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008) · 2008 Eighth IEEE International Conference on Data Mining · doi:10.1109/icdm.2008.17 · Cited by 6,601 · cited 1×
“IF Isolation forest (later termed “IF”) is another novelty detection method used here [27].”
MethodLOF: identifying density-based local outliers
Breunig, M. M., Kriegel, H.-P., Ng, R. T., & Sander, J. (2000) · ACM SIGMOD Record · doi:10.1145/335191.335388 · Cited by 5,207
LOF: identifying density-based local outliers
Breunig, M. M., Kriegel, H.-P., Ng, R. T., & Sander, J. (2000) · Proceedings of the 2000 ACM SIGMOD international conference on Management of data · doi:10.1145/342009.335388 · Cited by 4,149 · cited 9×
“One exception to this is for LOF/XGAP512 (Fig 7) which shows an average AUC that is less sensitive to increasing problem complexity (for the range of problems tested here).”
BackgroundMethodInfluentialLarge Scale GAN Training for High Fidelity Natural Image Synthesis
Brock, A., Donahue, J., & Simonyan, K. (2018) · arXiv · doi:10.48550/arxiv.1809.11096 · Cited by 3,717
Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
Schlegl, T., Seeböck, P., Waldstein, S. M., Schmidt-Erfurth, U., & Langs, G. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-59050-9_12 · Cited by 2,627
Pimentel, M. A. F., Clifton, D. A., Clifton, L., & Tarassenko, L. (2014) · Signal Processing · doi:10.1016/j.sigpro.2013.12.026 · Cited by 1,649 · cited 1×
“Prior work Past work in ND goes far and wide, and started with methods primarily grounded on classical machine learning (for recent surveys see [14,31,33], and more domain specific surveys [2, 4, 25]), including approaches such as [7,13,15].”
MethodGraph based anomaly detection and description: a survey
Akoglu, L., Tong, H., & Koutra, D. (2015) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-014-0365-y · Cited by 1,504 · cited 1×
“Prior work Past work in ND goes far and wide, and started with methods primarily grounded on classical machine learning (for recent surveys see [14,31,33], and more domain specific surveys [2, 4, 25]), including approaches such as [7,13,15].”
MethodHigh-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning
Erfani, S. M., Rajasegarar, S., Karunasekera, S., & Leckie, C. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.03.028 · Cited by 1,162
Zero-Shot Learning Through Cross-Modal Transfer
Socher, R., Ganjoo, M., Sridhar, H., Bastani, O., Manning, C. D., & Ng, A. Y. (2013) · arXiv · doi:10.48550/arxiv.1301.3666 · Cited by 997
Cited by
Uninformed Students: Student-Teacher Anomaly Detection With Discriminative Latent Embeddings
Bergmann, P., Fauser, M., Sattlegger, D., & Steger, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00424 · Cited by 990
Bergmann, P., Batzner, K., Fauser, M., Sattlegger, D., & Steger, C. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01400-4 · Cited by 602
“A popular approach is to select an arbitrary subset of classes, re-label them as outliers, and train a novelty detection system solely on the remaining inlier classes (An and Cho 2015; Chalapathy et al. 2018; Ruff et al. 2018; Burlina et al. 2019).”
BackgroundWeakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning
Tian, Y., Pang, G., Chen, Y., Singh, R., Verjans, J. W., & Carneiro, G. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00493 · Cited by 557
Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization
Bergmann, P., Batzner, K., Fauser, M., Sattlegger, D., & Steger, C. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01578-9 · Cited by 286
Addressing Artificial Intelligence Bias in Retinal Diagnostics
Burlina, P., Joshi, N., Paul, W., Pacheco, K. D., & Bressler, N. M. (2021) · Translational Vision Science & Technology · doi:10.1167/tvst.10.2.13 · Cited by 138
Self-citationNotice of Removal: Multiresolution Knowledge Distillation for Anomaly Detection
Salehi, M., Sadjadi, N., Baselizadeh, S., Rohban, M. H., & Rabiee, H. R. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01466 · Cited by 97
Yan, Y., Wang, D., Zhou, G., & Chen, Q. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3107586 · Cited by 60
A Comprehensive Survey on Generative AI Solutions in IoT Security
López Delgado, J. L., & López Ramos, J. A. (2024) · Electronics · doi:10.3390/electronics13244965 · Cited by 33
Metadata
- Authors
- Burlina, P., Joshi, N., & Wang, I.-J.
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 11499-11508
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2982324952
- Cited by
- 49
- References
- 9
- FWCI
- 2.60
- 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.