Abstract
The superior performance of object detectors is often established under the condition that the test samples are in the same distribution as the training data. However, in most practical applications, out-of-distribution (OOD) instances are inevitable and usually lead to detection uncertainty. In this work, the Feature structured OOD-IDentification (FOOD-ID) model is proposed to reduce the uncertainty of detection results by identifying the OOD instances. Instead of outputting each detection result directly, FOOD-ID uses a likelihood-based measuring mechanism to identify whether the feature satisfies the corresponding class distribution and outputs the OOD results separately. Specifically, the clustering-oriented feature structuration is firstly developed using class-specified prototypes and Attractive-Repulsive loss for more discriminative feature representation and more compact distribution. With the structured features space, the density distribution of all training categories is estimated based on a class-conditional normalizing flow, which is then used for the OOD identification in the test stage. The proposed FOOD-ID can be easily applied to various object detectors including anchor-based frameworks and anchor-free frameworks. Extensive experiments on the PASCAL VOC-IO dataset and an industrial defect dataset demonstrate that FOOD-ID achieves satisfactory OOD identification performance, with which the certainty of detection results is improved significantly.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ardizzone, L., Mackowiak, R., Rother, C., Kothe, U.: Training normalizing flows with the information bottleneck for competitive generative classification. arXiv:Learning (2020)
Bendale, A., Boult, T.E.: Towards open set deep networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1563–1572 (2016)
Choi, J., Chun, D., Kim, H., Lee, H.J.: Gaussian YOLOv3: an accurate and fast object detector using localization uncertainty for autonomous driving. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 502–511 (2019)
Dhamija, A., Günther, M., Ventura, J., Boult, T.: The overlooked elephant of object detection: open set, pp. 1010–1019 (2020). https://doi.org/10.1109/WACV45572.2020.9093355
Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP. ArXiv abs/1605.08803 (2017)
Du, X., Wang, Z., Cai, M., Li, S.: VOS: learning what you don’t know by virtual outlier synthesis. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=TW7d65uYu5M
Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: CenterNet: keypoint triplets for object detection. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 6568–6577 (2019)
Everingham, M., Gool, L.V., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. ArXiv abs/1506.02142 (2016)
Gawlikowski, J., et al.: A survey of uncertainty in deep neural networks. ArXiv abs/2107.03342 (2021)
Ge, Z., Demyanov, S., Chen, Z., Garnavi, R.: Generative OpenMax for multi-class open set classification. ArXiv abs/1707.07418 (2017)
Girshick, R.B.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1440–1448 (2015)
Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Harakeh, A., Smart, M., Waslander, S.L.: BayesOD: a Bayesian approach for uncertainty estimation in deep object detectors. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 87–93. IEEE (2020)
Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136 (2016)
Hsu, Y.C., Shen, Y., Jin, H., Kira, Z.: Generalized ODIN: detecting out-of-distribution image without learning from out-of-distribution data. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10948–10957 (2020)
Hüllermeier, E., Waegeman, W.: Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods. Mach. Learn. 110, 457–506 (2021)
Kaur, R., Jha, S., Roy, A., Park, S., Sokolsky, O., Lee, I.: Detecting OODs as datapoints with high uncertainty. arXiv preprint arXiv:2108.06380 (2021)
Kong, T., Sun, F., Liu, H., Jiang, Y., Li, L., Shi, J.: FoveaBox: Beyound anchor-based object detection. IEEE Trans. Image Process. 29, 7389–7398 (2020)
Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles. In: NIPS (2017)
Lee, K., Lee, K., Lee, H., Shin, J.: A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In: NeurIPS (2018)
Lee, Y., won Hwang, J., Kim, H., Yun, K., Park, J.: Localization uncertainty estimation for anchor-free object detection. ArXiv abs/2006.15607 (2020)
Li, X., Wang, W., Hu, X., Li, J., Tang, J., Yang, J.: Generalized focal loss V2: learning reliable localization quality estimation for dense object detection. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11627–11636 (2021)
Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv:Learning (2018)
Lin, T.Y., Goyal, P., Girshick, R.B., He, K., Dollár, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42, 318–327 (2020)
Liu, W., et al.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Liu, W., Wang, X., Owens, J.D., Li, Y.: Energy-based out-of-distribution detection. ArXiv abs/2010.03759 (2020)
Miller, A., Fisch, A., Dodge, J., Karimi, A.H., Bordes, A., Weston, J.: Key-value memory networks for directly reading documents. arXiv preprint arXiv:1606.03126 (2016)
Miller, D., Nicholson, L., Dayoub, F., Sünderhauf, N.: Dropout sampling for robust object detection in open-set conditions. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 1–7 (2018)
Miller, D., Sünderhauf, N., Milford, M., Dayoub, F.: Class anchor clustering: a loss for distance-based open set recognition. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 3569–3577 (2021)
Miller, D., Sunderhauf, N., Milford, M., Dayoub, F.: Uncertainty for identifying open-set errors in visual object detection. IEEE Robot. Autom. Lett. 7, 215–222 (2022)
Neal, L., Olson, M., Fern, X., Wong, W.-K., Li, F.: Open set learning with counterfactual images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 620–635. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01231-1_38
Ovadia, Y., et al.: Can you trust your model’s uncertainty? Evaluating predictive uncertainty under dataset shift. In: NeurIPS (2019)
Oza, P., Patel, V.M.: C2AE: class conditioned auto-encoder for open-set recognition. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2302–2311 (2019)
Park, H., Noh, J., Ham, B.: Learning memory-guided normality for anomaly detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14372–14381 (2020)
Perera, P., et al.: Generative-discriminative feature representations for open-set recognition. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11811–11820 (2020)
Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788 (2016)
Ren, J., et al.: Likelihood ratios for out-of-distribution detection. In: NeurIPS (2019)
Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137–1149 (2015)
Steinhardt, J., Liang, P.S.: Unsupervised risk estimation using only conditional independence structure. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Sukhbaatar, S., Weston, J., Fergus, R., et al.: End-to-end memory networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)
Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 9626–9635 (2019)
Vyas, A., Jammalamadaka, N., Zhu, X., Das, D., Kaul, B., Willke, T.L.: Out-of-distribution detection using an ensemble of self supervised leave-out classifiers. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 560–574. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_34
Wang, G., Li, W., Aertsen, M., Deprest, J.A., Ourselin, S., Vercauteren, T.K.M.: Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks. Neurocomputing 335, 34–45 (2019)
Weston, J., Chopra, S., Bordes, A.: Memory networks. arXiv preprint arXiv:1410.3916 (2014)
Yoshihashi, R., Shao, W., Kawakami, R., You, S., Iida, M., Naemura, T.: Classification-reconstruction learning for open-set recognition. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4011–4020 (2019)
Yu, Q., Aizawa, K.: Unsupervised out-of-distribution detection by maximum classifier discrepancy. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 9517–9525 (2019)
Zhu, C., He, Y., Savvides, M.: Feature selective anchor-free module for single-shot object detection. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 840–849 (2019)
Zisselman, E., Tamar, A.: Deep residual flow for out of distribution detection. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13991–14000 (2020)
Acknowledgement
This work was supported in part by the National Natural Science Fund of China (61971281), the National Key R &D Program of China (2021YFD1400104), the Shanghai Municipal Science and Technology Major Project (2021SHZDZX0102), and the Science and Technology Commission of Shanghai Municipality (18DZ2270700).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, R., Zhang, C., Zhou, H., Shi, C., Luo, Y. (2022). Out-of-Distribution Identification: Let Detector Tell Which I Am Not Sure. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13670. Springer, Cham. https://doi.org/10.1007/978-3-031-20080-9_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-20080-9_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20079-3
Online ISBN: 978-3-031-20080-9
eBook Packages: Computer ScienceComputer Science (R0)