Abstract
In Machine Learning systems, several factors impact the performance of a trained model. The most important ones include model architecture, the amount of training time, the dataset size and diversity. We present a method for analyzing datasets from a use-case scenario perspective, detecting and quantifying out-of-distribution (OOD) data on dataset level.
Our main contribution is the novel use of similarity metrics for the evaluation of the robustness of a model by introducing relative Fréchet Inception Distance (FID) and relative Kernel Inception Distance (KID) measures. These relative measures are relative to a baseline in-distribution dataset and are used to estimate how the model will perform on OOD data (i.e. estimate the model accuracy drop). We find a correlation between our proposed relative FID/relative KID measure and the drop in Average Precision (AP) accuracy on unseen data.
This work was partially funded by Sweden’s Innovation Agency and the Swedish Foundation for Strategic Research.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bińkowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs. arXiv preprint arXiv:1801.01401 (2018)
Cluzeau, J.M., et al.: Concepts of design assurance for neural networks (CODANN). Public Rep. Extract Version 1, 1–104 (2020)
Fremont, D.J., Dreossi, T., Ghosh, S., Yue, X., Sangiovanni-Vincentelli, A.L., Seshia, S.A.: Scenic: a language for scenario specification and scene generation. In: Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation, pp. 63–78 (2019)
Gaidon, A., Wang, Q., Cabon, Y., Vig, E.: Virtual worlds as proxy for multi-object tracking analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4340–4349 (2016)
Guillory, D., Shankar, V., Ebrahimi, S., Darrell, T., Schmidt, L.: Predicting with confidence on unseen distributions. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1134–1144 (2021)
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Kullback, S., Leibler, R.A.: On information and sufficiency. Ann. Math. Stat. 22(1), 79–86 (1951)
Lin, T., et al.: Microsoft COCO: common objects in context. CoRR abs/1405.0312 (2014). http://arxiv.org/abs/1405.0312
Lindén, J., et al.: Curating datasets for visual runway detection. In: 2021 IEEE/AIAA 40th Digital Avionics Systems Conference (DASC), pp. 1–9. IEEE (2021)
Masana, M., Ruiz, I., Serrat, J., van de Weijer, J., Lopez, A.M.: Metric learning for novelty and anomaly detection. arXiv preprint arXiv:1808.05492 (2018)
Schäfer, M., Strohmeier, M., Lenders, V., Martinovic, I., Wilhelm, M.: Bringing up OpenSky: a large-scale ADS-B sensor network for research. In: IPSN-14 Proceedings of the 13th International Symposium on Information Processing in Sensor Networks, pp. 83–94. IEEE (2014)
Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 843–852 (2017)
Sun, Y., Ming, Y., Zhu, X., Li, Y.: Out-of-distribution detection with deep nearest neighbors. In: International Conference on Machine Learning, pp. 20827–20840. PMLR (2022)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Techapanurak, E., Suganuma, M., Okatani, T.: Hyperparameter-free out-of-distribution detection using softmax of scaled cosine similarity. arXiv preprint arXiv:1905.10628 (2019)
Theis, L., Oord, A.v.d., Bethge, M.: A note on the evaluation of generative models. arXiv preprint arXiv:1511.01844 (2015)
Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696 (2022)
Yang, J., Zhou, K., Li, Y., Liu, Z.: Generalized out-of-distribution detectionasurvey. arXiv preprint arXiv:2110.11334 (2021)
Zaidi, S.S.A., Ansari, M.S., Aslam, A., Kanwal, N., Asghar, M., Lee, B.: A survey of modern deep learning based object detection models. Digit. Signal Process. 126, 103514 (2022)
Zilly, J., Zilly, H., Richter, O., Wattenhofer, R., Censi, A., Frazzoli, E.: The Frechet distance of training and test distribution predicts the generalization gap (2019)
Acknowledgements
The authors would like to thank members of the HERO group at Mälardalen University for constructive discussions and feedback, especially from Seyedhamidreza Mousavi.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lindén, J., Forsberg, H., Daneshtalab, M., Söderquist, I. (2023). Evaluating the Robustness of ML Models to Out-of-Distribution Data Through Similarity Analysis. In: Abelló, A., et al. New Trends in Database and Information Systems. ADBIS 2023. Communications in Computer and Information Science, vol 1850. Springer, Cham. https://doi.org/10.1007/978-3-031-42941-5_30
Download citation
DOI: https://doi.org/10.1007/978-3-031-42941-5_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42940-8
Online ISBN: 978-3-031-42941-5
eBook Packages: Computer ScienceComputer Science (R0)