![](bg8.png)
on CIFAR10. We believe that these future research
questions combined with the results from this paper
pave the way for safer use of neural networks.
REFERENCES
Betta, G., Capriglione, D., Liguori, C., and Paolillo, A.
(2011). Uncertainty Evaluation in Face Recognition
Algorithms. IEEE International Instrumentation and
Measurement Technology Conference (I2MTC).
Boone, L., Biparva, M., Forooshani, P. M., Ramirez, J.,
Masellis, M., Bartha, R., Symons, S., Strother, S.,
Black, S. E., Heyn, C., Martel, A. L., Swartz, R. H.,
and Goubran, M. (2022). ROOD-MRI: Benchmarking
the Robustness of Deep Learning Segmentation Mod-
els to Out-of-Distribution and Corrupted Data in MRI.
Technical report.
Chang, J., Lan, Z., Cheng, C., and Wei, Y. (2020). Data
Uncertainty Learning in Face Recognition. In CVPR.
Corbi
`
ere, C., Thome, N., Bar-Hen, A., Cord, M., and P
´
erez,
P. (2019). Addressing Failure Prediction By Learning
Model Confidence. In NeurIPS.
Cubuk, E. D., Zoph, B., Mane, D., Vasudevan, V., and Le,
Q. V. (2019). Autoaugment: Learning augmentation
strategies from data. In CVPR.
DeVries, T. and Taylor, G. W. (2018). Learning Confidence
for Out-of-Distribution Detection in Neural Networks.
Technical report.
Drucker, H. and Cun, Y. L. (1992). Improving General-
ization Performance Using Double Backpropagation.
IEEE Transactions on Neural Networks.
Fort, S., Ren, J., and Lakshminarayanan, B. (2021). Ex-
ploring the Limits of Out-of-Distribution Detection.
In NeurIPS.
He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Resid-
ual Learning for Image Recognition. Technical report.
Hendrycks, D., Basart, S., Mazeika, M., Zou, A., Kwon, J.,
Mostajabi, M., Steinhardt, J., and Song, D. (2019a).
A Benchmark for Anomaly Segmentation.
Hendrycks, D., Basart, S., Mazeika, M., Zou, A., Kwon, J.,
Mostajabi, M., Steinhardt, J., and Song, D. (2019b).
Scaling Out-of-Distribution Detection for Real-World
Settings. In ICML.
Hendrycks, D. and Gimpel, K. (2016). A Baseline for De-
tecting Misclassified and Out-of-Distribution Exam-
ples in Neural Networks. In ICLR.
Hendrycks, D., Mazeika, M., and Dietterich, T. (2018).
Deep Anomaly Detection with Outlier Exposure. In
ICLR.
Huang, R. and Li, Y. (2021). MOS: Towards Scaling Out-
of-distribution Detection for Large Semantic Space.
In CVPR.
Ilyas, A., Santurkar, S., Tsipras, D., Engstrom, L., Tran, B.,
and Madry, A. (2019). Adversarial Examples Are Not
Bugs, They Are Features. In NeurIPS.
Kuangliu (2021). Kuangliu/Pytorch-CIFAR: 95.47% on CI-
FAR10 with pytorch.
Lee, K., Lee, H., Lee, K., and Shin, J. (2017). Training
Confidence-calibrated Classifiers for Detecting Out-
of-Distribution Samples. In ICLR.
Lee, K., Lee, K., Lee, H., and Shin, J. (2018). A Simple
Unified Framework for Detecting Out-of-Distribution
Samples and Adversarial Attacks. NeurIPS.
Liang, S., Li, Y., and Srikant, R. (2017). Enhancing the
Reliability of Out-of-Distribution Image Detection in
Neural Networks. ICLR.
Liu, W., Wang, X., Owens, J. D., and Li, Y. (2020). Energy-
based Out-of-distribution Detection. In NeurIPS.
Mehrtash, A., Wells, W. M., Tempany, C. M., Abolmae-
sumi, P., and Kapur, T. (2020). Confidence Calibra-
tion and Predictive Uncertainty Estimation for Deep
Medical Image Segmentation. IEEE Transactions on
Medical Imaging.
Nesterov, Y. E. (1983). A Method of Solving a Convex
Programming Problem With Convergence rate. Pro-
ceedings of the USSR Academy of Sciences.
Raghu, M., Blumer, K., Sayres, R., Obermeyer, Z., Klein-
berg, R., Mullainathan, S., and Kleinberg, J. (2019).
Direct Uncertainty Prediction for Medical Second
Opinions. In ICML.
Roady, R., Hayes, T. L., Kemker, R., Gonzales, A., and
Kanan, C. (2019). Are Out-of-Distribution Detection
Methods Effective on Large-Scale Datasets? Techni-
cal report.
Sastry, C. S. and Oore, S. (2020). Detecting Out-of-
Distribution Examples with Gram Matrices. In ICML.
Sun, Y., Guo, C., and Li, Y. (2021). ReAct: Out-of-
distribution Detection With Rectified Activations. In
NeurIPS.
Vojir, T., Sipka, T., Aljundi, R., Chumerin, N., Olmeda
Reino, D., and Matas, J. (2021). Road Anomaly De-
tection by Partial Image Reconstruction with Segmen-
tation Coupling. In ICCV.
Winkens, J., Bunel, R., Roy, A. G., Stanforth, R., Natara-
jan, V., Ledsam, J. R., MacWilliams, P., Kohli, P.,
Karthikesalingam, A., Kohl, S., Cemgil, T., Eslami,
S. M. A., and Ronneberger, O. (2020). Contrastive
Training for Improved Out-of-Distribution Detection.
Technical report.
Yang, J., Wang, H., Feng, L., Yan, X., Zheng, H.,
Zhang, W., and Liu, Z. (2021a). Generalized Out-of-
Distribution Detection: A Survey. Technical report.
Yang, J., Wang, H., Feng, L., Yan, X., Zheng, H., Zhang,
W., and Liu, Z. (2021b). Semantically Coherent Out-
of-Distribution Detection. In ICCV.
Zhang, H., Cisse, M., Dauphin, Y. N., and Lopez-Paz, D.
(2018). MixUp: Beyond Empirical Risk Minimiza-
tion. In ICLR.
Zhong, Z., Zheng, L., Kang, G., Li, S., and Yang, Y. (2020).
Random Erasing Data augmentation. In Proceedings
of the AAAI Conference on Artificial Intelligence.
Zisselman, E. and Tamar, A. (2020). Deep Residual Flow
for Out of Distribution Detection. In CVPR.
VISAPP 2023 - 18th International Conference on Computer Vision Theory and Applications
730