The DOI matches its Crossref record; 42 of the 45 references it cites were found in a registry or an index.
Generalized ODIN: Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data
Open accessAbstract
Deep neural networks have attained remarkable performance when applied to data that comes from the same distribution as that of the training set, but can significantly degrade otherwise. Therefore, detecting whether an example is out-of-distribution (OoD) is crucial to enable a system that can reject such samples or alert users. Recent works have made significant progress on OoD benchmarks consisting of small image datasets. However, many recent methods based on neural networks rely on training or tuning with both in-distribution and out-of-distribution data. The latter is generally hard to define a-priori, and its selection can easily bias the learning. We base our work on a popular method ODIN, proposing two strategies for freeing it from the needs of tuning with OoD data, while improving its OoD detection performance. We specifically propose to decompose confidence scoring as well as a modified input pre-processing method. We show that both of these significantly help in detection performance. Our further analysis on a larger scale image dataset shows that the two types of distribution shifts, specifically semantic shift and non-semantic shift, present a significant difference in the difficulty of the problem, providing an analysis of when ODIN-like strategies do or do not work.
Overview
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
Verification
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The perturbation magnitude is determined on a small held-out validation set.”
From QUTE: Quantifying Uncertainty in TinyML with Early-exit-assisted ensembles for model-monitoring (2024) · cites this paper as Hsu et al., 2020
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This suggests that general OOD-detectors are not automatically effective for CID detection”
From QUTE: Quantifying Uncertainty in TinyML with Early-exit-assisted ensembles for model-monitoring (2024) · cites this paper as Hsu et al., 2020
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Generalized-ODIN (G-ODIN) (Hsu et al., 2020): a generalized OOD detection method that decomposes the confidence score and introduces a preprocessing layer that perturbs the inputs for better OOD detection.”
From QUTE: Quantifying Uncertainty in TinyML with Early-exit-assisted ensembles for model-monitoring (2024) · cites this paper as Hsu et al., 2020
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
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,889
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
Identity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741
Intriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
Zagoruyko, S., & Komodakis, N. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.87 · Cited by 7,244
Dropout as a bayesian approximation: Representing model uncertainty in deep learning
Gal, Y., & Ghahramani, Z. (2015) · arXiv · doi:10.48550/arxiv.1506.02142 · Cited by 6,471
Reading digits in natural images with unsupervised feature learning
Netzer, Y. (2024) · doi:10.57702/e7wwo0zk · Cited by 4,261
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
Lakshminarayanan, B., Pritzel, A., & Blundell, C. (2016) · arXiv · doi:10.48550/arxiv.1612.01474 · Cited by 3,666
Research works printed but not linked: 1
- shafaei, 0, A less biased evaluation of ood sample detectors, Proceedings of the British Machine Vision Conference (BMVC)
Cited by
Sorted by citations
A survey of uncertainty in deep neural networks
Gawlikowski, J., Tassi, C. R. N., Ali, M., Lee, J., Humt, M., Feng, J., Kruspe, A., Triebel, R., Jung, P., Roscher, R., et al. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10562-9 · Cited by 1,670
Energy-based Out-of-distribution DetectionPreprint
Liu, W., Wang, X., Owens, J. D., & Li, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.03759 · Cited by 744
Generalized Out-of-Distribution Detection: A Survey
Yang, J., Zhou, K., Li, Y., & Liu, Z. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02117-4 · Cited by 884
GAN-based anomaly detection: A review
Xia, X., Pan, X., Li, N., He, X., Ma, L., Zhang, X., & Ding, N. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.12.093 · Cited by 423
Adversarial Reciprocal Points Learning for Open Set Recognition
Chen, G., Peng, P., Wang, X., & Tian, Y. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3106743 · Cited by 388
Metadata
- Authors
- Hsu, Y.-C., Shen, Y., Jin, H., & Kira, Z.
- Affiliations
- Georgia Institute of Technology (US)
- Samsung (United States) (US)
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 10948-10957
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3034230713
- Cited by
- 499
- References
- 45
- Citations by year
- 2026: 38 · 2025: 83 · 2024: 98 · 2023: 114 · 2022: 61 · 2021: 92 · 2020: 12
- FWCI
- 26.61
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- out-of-distribution detection, Odin, confidence calibration, distribution shift, semantic change, image classification, anomaly detection
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
