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
Items 401–499 of 499
Label Smoothed Embedding Hypothesis for Out-of-Distribution DetectionPreprint
Bahri, D., Jiang, H., Tay, Y., & Metzler, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.05131 · Cited by 1
Joint Distribution across Representation Space for Out-of-Distribution DetectionPreprint
Xu, J., Zhu, S., Li, Z., & Xu, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.12344
Lightweight Detection of Out-of-Distribution and Adversarial Samples via Channel Mean Discrepancy.Preprint
Dong, X., Guo, J., Ting, W.-T., & Kung, H. T. (2021) · arXiv (Cornell University)
Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLUPreprint
Shen, Y., Hsu, Y.-C., Ray, A., & Jin, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.14464
Self-citationSample-free white-box out-of-distribution detection for deep learning
Begon, J.-M., & Geurts, P. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00367
Selection of Class-conditional Filters for Semantic Shifted OOD Detection
Yu, Y., Shin, S., Kim, J., & Lee, K. (2021) · International Conference on Ubiquitous Robots (UR) · doi:10.1109/ur52253.2021.9494630
A novel network training approach for open set image recognitionPreprint
Hossaina, T., Teng, S. W., Lu, G., & Sohel, F. A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.12756
Generalizing Neural Networks by Reflecting Deviating Data in ProductionPreprint
Xiao, Y., Lin, Y., Beschastnikh, I., Sun, C., Rosenblum, D. S., & Dong, J. S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.02718
Class-wise Thresholding for Detecting Out-of-Distribution Data.Preprint
Guarrera, M., Jin, B., Lin, T.-W., Zuluaga, M. A., Chen, Y., & Sangiovanni-Vincentelli, A. L. (2021) · arXiv (Cornell University)
Mixture Outlier Exposure for Out-of-Distribution Detection in Fine-grained Settings.Preprint
Zhang, J., Inkawhich, N., Linderman, R., Chen, Y., & Li, H. H. (2021) · arXiv (Cornell University)
Lyons, N., Santra, A., & Pandey, A. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-3-030-98886-9_12
Unboundedness of Linear Regions of Deep ReLU Neural Networks
Ponomarchuk, A., Christoph Koutschan, C., & Moser, B. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-14343-4_1
Marvasti, A. E., Marvasti, E. E., & Bağcı, U. (2022) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme55909.2022.9988128 · Cited by 1
Natural robustness of machine learning in the open world
Wei, H. (2023) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/166625
Out‐of‐distribution detection based on multi‐classifiers
Jiang, W., & Yu, Y. (2023) · Cognitive Computation and Systems · doi:10.1049/ccs2.12079
EXOT: Exit-aware Object Tracker for Safe Robotic Manipulation of Moving Object
Kim, H., Yoon, H., Kim, M., Han, D.-S., & Zhang, B. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160481
Data-Locked Knowledge Distillation with Ready-To-Use Substitutes
Mei, J.-P., Chen, J., & Chu, X. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10192003
Lust, J., & Condurache, A. P. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191233
Calculating Class-Wise Weighted Feature Norm for Detecting Out-of-Distribution Samples
Yu, Y., Shin, S., & Lee, K. (2023) · International Conference on Ubiquitous Robots (UR) · doi:10.1109/ur57808.2023.10202349
On the detection of Out-Of-Distribution samples in Multiple Instance LearningPreprint
Bescond, L. L., Vakalopoulou, M., Christodoulidis, S., André, F., & Talbot, H. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.05528
Familiarity-Based Open-Set Recognition Under Adversarial Attacks
Enevoldsen, P., Gundersen, C., Lang, N., Belongie, S., & Igel, C. (2023) · Research at the University of Copenhagen (University of Copenhagen) · doi:10.48550/arxiv.2311.05006
Improving Out-of-Distribution Detection with Margin-Based Prototype Learning
Liu, J., Ren, Y., Li, W., Zheng, Y., & Wang, C. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-8148-9_12
Boosting Out-of-Distribution Detection with Sample Weighting
Ke, A., Chen, W., Feng, C., & Xie, X. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8435-0_17
Design of Opinion Leader Identification System for Hot Public Opinion
Cai, X., Hong, L., Pan, C., & Han, Y. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-9239-3_39
Reliable Classification using Compact Support Probabilistic PCA
Zhang, J., & Barbu, A. (2023) · International Conference on Machine Learning and Applications · doi:10.1109/icmla58977.2023.00204
Methods for non-intrusive out-of-distribution images detection
Vlasova, A. V., Shkanaev, A. Y., & Sholomov, D. L. (2024) · International Conference on Machine Vision · doi:10.1117/12.3023403
Model Reprogramming Outperforms Fine-tuning on Out-of-distribution Data in Text-Image Encoders
Geng, A., & Chen, P. (2024) · IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · doi:10.1109/satml59370.2024.00034
Revealing semantic mappings across HAR datasets
Alevizaki, A., Pham, N., & Trigoni, N. (2024) · International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT) · doi:10.1109/dcoss-iot61029.2024.00023
Image Dataset Quality Assessment Through Descriptive Out-of-Distribution Detection
Kharma, S., & Großmann, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70893-0_11
Out-of-Distribution Detection Based on Multiple Metrics Fusion of Network Hidden Features
Zhu, Q., & He, Y. (2024) · IEEE Access · doi:10.1109/access.2024.3471693
Learning Non-linear Invariants for Unsupervised Out-of-Distribution Detection
Doorenbos, L., Sznitman, R., & Márquez-Neila, P. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72943-0_18
Supervised Mixup: Protecting the Likely Classes for Adversarial Robustness
Agarwal, A., Mayank Vatsa, A., Singh, R., & Ratha, N. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78169-8_3
Fuzzy Logic Algorithm for Index Optimization in Database Query
Wang, J. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-97-7710-5_62
TagFog: Textual Anchor Guidance and Fake Outlier Generation for Visual Out-of-Distribution DetectionPreprint
Chen, J., Zhang, T., Zheng, W., & Wang, R. (2024) · Qeios · doi:10.32388/flrme3 · Cited by 1
Closed loop networks for open-set semi-supervised learning
Ouyang, J., Meng, Q., Li, X., Zhang, Z., Li, C., & Wang, W. (2024) · Information Sciences · doi:10.1016/j.ins.2024.121788
Nazar: Monitoring and Adapting ML Models on Mobile Devices
Hao, W., Wang, Z., Hong, L., Li, L., Karayanni, N., Dasbach-Prisk, A., Mao, C., Yang, J., & Cidon, A. (2025) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3669940.3707246
Cuevas, F. G., & Schmid, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-97-8702-9_32
Integrating Logit Space Embeddings for Reliable Out-of-Distribution Detection
Komini, V., & Girdzijauskas, Š. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-82484-5_19
Out-of-Distribution Detectors: Not Yet Primed for Practical Deployment
Wu, C., Ding, W., Huang, X., & Bensalem, S. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888258
MIB: Mixed Information Bottleneck for Out-of-Distribution Keyword Spotting
Saidutta, Y. M., Srinivasa, R. S., Cho, J., Lee, C.-H., Yang, C. J., Shen, Y., & Jin, H. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889347
Self-citationCRAFT: Class Ranking Aware Fine-Tuning for Enhanced Out-of-Distribution Detection
Karunanayake, N., Seneviratne, S., & Chawla, S. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00405
Pan, D., Sheng, B., & Li, X. (2025) · Electronics · doi:10.3390/electronics14091881 · Cited by 1
TAG: Text Prompt Augmentation for Zero-Shot Out-of-Distribution Detection
Liu, X., & Zach, C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91585-7_15
Vijendran, M., Chen, S., Deng, J., & Shum, H. P. H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128905
Enabling Effective OOD Detection via Plug-and-Play Network for Mobile Visual Applications
Wang, Z., Dong, Q., Xing, T., Liu, Z., Li, Z., & Chen, X. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3586625
OSSOD-RS: Towards Open-set Semi-Supervised Object Detection In Remote Sensing
Tang, P., & Yang, C. (2025) · Journal of Physics Conference Series · doi:10.1088/1742-6596/3055/1/012023
ProGIP: Protecting Gradient-based Input Perturbation Approaches for OOD Detection From Soft Errors
Joshi, S. S., So, H., Park, S., Ko, W., Jung, J., Ko, Y., Hwang, U., Lee, K., & Shrivastava, A. (2025) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3761796
SLE: Out-of-Distribution Detection With Shallow Layer-Driven Enhancement
Yang, Z., Liu, C., & Qian, X. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3604940
Improved Out-of-Distribution Detection with Additive Angular Margin Loss
Ravikumar, D., Soufleri, E., & Roy, K. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00327
Wang, J., MacCormac, O. J., Rochford, W., Kujawa, A., Shapey, J., & Vercauteren, T. K. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04984-1_56
Out of Distribution Detection in Self-adaptive Robots with AI-powered Digital Twins
Isaku, E., Sartaj, H., Ali, S., Sanguino, B., Wang, T., Li, G., Zhang, H., & Peyrucain, T. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00281
ROMA: Regularization for Out-of-distribution Detection with Masked Autoencoders
Feng, X., Jiang, Y., Sha, H., & Zhang, Y. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209784
Out-of-distribution detection in text using statistical techniques
Raghavan, D., Bhandari, S., Banerjee, J., & Bandyopadhyay, S. (2025) · Discover Data · doi:10.1007/s44248-025-00091-x
Introducing “Inside” out of distribution
Lazebnik, T. (2025) · International Journal of Data Science and Analytics · doi:10.1007/s41060-025-00947-0
Unseen Attacks Identification in Intrusion Systems Using BERT and Logit Normalization
Adjewa, F., Esseghir, M., Merghem, L., & Emani, C. K. (2025) · IEEE International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob) · doi:10.1109/wimob66857.2025.11257491
Label tree semantic losses for rich multi-class medical image segmentation
Wang, J., MacCormac, O. J., Rochford, W., Kujawa, A., Shapey, J., & Vercauteren, T. K. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1841639
Enhancing Semi-Supervised Learners via Similarity-Based Self-Supervised Models
Lin, S., Hsieh, H., Lin, L., Chang, K.-C., Lu, J.-M., Lin, T.-J., & Chen, T.-F. (2025) · IEEE Interregional NEWCAS Conference (NEWCAS) · doi:10.1109/newcas64648.2025.11106967
Enriching Category Representations with LLMs Towards Robust Zero-Shot OOD Detection
Chao, D., Zhang, Y., Zhou, L., & Yang, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05962-8_2
A Simple and Effective Method for Uncertainty Quantification and OOD Detection
Ma, Y., Colburn, B., & Principe, J. C. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227940
Alotaibi, D. A., Zhou, J. J., Dong, Y., & Chen, F. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-6888-8_5
Unknown object detection by leveraging Segment Anything Model for labeling the OOD objects
Kanwal, S., Wahd, A. S., Lee, S., Jang, M., & Lee, S. (2025) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc66702.2025.11388538
Ashmore, B., & Chen, L. (2026) · World Wide Web · doi:10.1007/s11280-026-01406-x
Bipolar Joint Energy: Energy-Based Multi-Label OOD Detection with Bipolar Networks
Mishra, S., Moorthy, K. K., & Sundaram, S. (2025) · International Conference on Robotics, Automation and Artificial Intelligence (RAAI) · doi:10.1109/raai67517.2025.11423342
Protecting Deep Learning Systems Against Attack : Enhancing Adversarial Robustness and Detection
Picot, M. (2023) · theses.fr (ABES) · doi:10.70675/baaedc7fzdbaaz4337z89a4z5cb4d019c9f8
Securing Machine Learning Algorithms
Granese, F. (2023) · theses.fr (ABES) · doi:10.70675/34cfe525z600dz4a89z816dzd1f129eeeba8 · Cited by 21
Runtime safety monitoring of ML-based perception functions in autonomous systems
Ferreira, R. (2023) · theses.fr (ABES) · doi:10.70675/e815126ezfd23z4ebczabcdz5fb529197cf6 · Cited by 1
Gomes, E. D. C. (2024) · theses.fr (ABES) · doi:10.70675/016822ffzf521z4408zb481z2e410d5446bb
Robustness Analysis of Classifiers Against Out-of-Distribution and Adversarial Inputs
Chali, S. (2024) · theses.fr (ABES) · doi:10.70675/045f4849z9f1ez4973z8c70z8d4cedc8a05d
Atienza, N. (2025) · theses.fr (ABES) · doi:10.70675/81053b26z6d53z4f04zacc2zb3dd0156bba4
Out-Of-Distribution Detection Based on Total Variation Estimation
Ma, D., Su, Z., Yang, J., & Fei, H. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460881
Dynamic Prototype Refinement for out-of-Distribution Detection: Balancing Compactness and Diversity
Yang, C., Luo, Y., Feng, S., Xu, H., & Zhai, Z. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463474
A website fingerprinting attack with unsupervised out-of-distribution detection
Gao, Y., Zhao, J., Chen, C., Huang, S., Shi, L., Jiang, C., & Chen, B. (2026) · Cybersecurity · doi:10.1186/s42400-025-00398-x
Adaptive Prompt Learning via Gaussian Outlier Synthesis for Out-Of-Distribution Detection
Zhang, Y., She, D., & Zhou, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00310
One Model, Many Behaviors: Training-Induced Effects on Out-of-Distribution Detection
Krumpl, G., Avenhaus, H., & Possegger, H. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00402 · Cited by 2
Detecting Out-of-Distribution Objects through Class-Conditioned Inpainting
Nguyen, Q.-H., Zhou, J., Liu, Z., Bui, K.-H., Weinberger, K. Q., Chao, W., & Le, D. D. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00193
Adapter OOD: Conditional Generation of Out-of-Distribution Images for OOD Detection
Song, Y. (2026) · International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE) · doi:10.1109/aetcse69203.2026.11504379
A modified evidential deep learning fault diagnosis method for detecting out-of-distribution samples
Lu, H., Li, W., Xiong, B., Peng, H., Zhou, J., & Ke, J. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae6fda · Cited by 1
A Plug-and-Play New Fault Detection Method Based on Deep Compressed Sensing and Contrastive Learning
Wei, Q., Wang, X., Tian, X., & Cui, L. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3699750
Chen, Y.-H., Chen, T., Chen, S.-T., & Lin, P. (2026) · IEEE robotics and automation practice. · doi:10.1109/rap.2026.3700968
Ghamari, S., Esmaeilzehi, A., Ahmad, M. O., & Swamy, M. N. S. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.106076
Benefiting From OOD Samples in Open-Set Semi-Supervised Object Detection
Zou, Y., Wang, K., Li, J., Wang, C., Liu, S., Lin, L., & Li, G. (2026) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2026.3659534
Typical-smoothed truncation for out-of-distribution detection
Wang, F., He, R., Gao, W., & Yin, Y. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116434
Hamzaoui, M., Aoueileyine, M. O.-E., Filali, I., & Bouallegue, R. (2026) · Scientific Reports · doi:10.1038/s41598-026-59151-0
Out-of-Distribution Detection in Computer Vision: A Comprehensive Survey and Research Challenges
Sayyed, S., Rifat, S., Zhang, M., Swami, A., Lucia, M. D., Bastian, N. D., & Restuccia, F. (2026) · ACM Computing Surveys · doi:10.1145/3822404
Exploiting Local Flatness for Efficient Out-of-Distribution Detection
Park, S. J., Jung, H., Lee, D., & Lee, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37553-7_28
Through the Looking Glass: A Dual Perspective on Weakly Supervised Few-Shot Segmentation
Ma, J., Xie, G.-S., Zhao, F., & Li, Z. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3708050
GradAlign: Detecting Out-of-Distribution Samples via Gradient Concentration
Gu, J., Sun, Y., Tang, H., & Li, Z. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02926-9
Dario, M., Chenevier, F., Delmas, K., Guerin, J. M., & Guiochet, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31666-0_40
When Models Leave the Training Distribution: A Tutorial on OOD Detection
Seneviratne, S., Denipitiyage, D., Chawla, S., & Menon, A. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3816455
Feature-Alteration Robustness for Out-of-Distribution Detection
Jiang, X., Liu, F., Fang, Z., Chen, H., Liu, T., Zheng, F., & Han, B. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3723999
Komini, V. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37654-1_2
CF-OOD+: Concentration-Free Out-of-Distribution Detection with multi-layer aggregation
Angiulli, F., Fassetti, F., & Zupi, M. P. (2026) · Information Systems · doi:10.1016/j.is.2026.102807
Long-Tailed Out-Of-Distribution Detection With Refined Separate Class Learning
Feng, S., Ge, Y., Zhang, B., Du, Y., Chen, M., Wang, C., & Feng, L. (2026) · doi:10.1109/cvprf71909.2026.00634
Catalyst: Out-of-Distribution Detection via Elastic Scaling
Hassan, A., Ngo, T., Shafiq, S., & Medvidović, N. (2026) · doi:10.1109/cvprf71909.2026.00160
RASA: Reliability-Aware Selective Adaptation via Hybrid Reliability Threshold
Liu, Z., Wang, Y., Ji, J., Tang, Y., & He, Z. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729341
Meta open set filtering for open set recognition
Guo, P., WANG, S., Wang, J., & Sun, Y. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.105001
Salehi, M., Mirzaei, H., Hendrycks, D., Li, Y., Rohban, M. H., & Sabokrou, M. (2021) · arXiv · doi:10.48550/arxiv.2110.14051 · Cited by 118
Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
Malinin, A., Band, N., Ganshin, A., Chesnokov, G., Gal, Y., Gales, M. J. F., Noskov, A., Ploskonosov, A., Prokhorenkova, L., Provilkov, I., et al. (2021) · arXiv · doi:10.48550/arxiv.2107.07455 · Cited by 48
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
