Abstract
Widespread application of computer vision systems in real world tasks is currently hindered by their unexpected behavior on unseen examples. This occurs due to limitations of empirical testing on finite test sets and lack of systematic methods to identify the breaking points of a trained model. In this work we propose semantic adversarial editing, a method to synthesize plausible but difficult data points on which our target model breaks down. We achieve this with a differentiable object synthesizer which can change an object’s appearance while retaining its pose. Constrained adversarial optimization of object appearance through this synthesizer produces rare/difficult versions of an object which fool the target object detector. Experiments show that our approach effectively synthesizes difficult test data, dropping the performance of YoloV3 detector by more than 20 mAP points by changing the appearance of a single object and discovering failure modes of the model. The generated semantic adversarial data can also be used to robustify the detector through data augmentation, consistently improving its performance in both standard and out-of-dataset-distribution test sets, across three different datasets.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alaifari, R., Alberti, G.S., Gauksson, T.: ADef: an iterative algorithm to construct adversarial deformations. In: Proceedings of the International Conference on Learning Representations (ICLR) (2019)
Alcorn, M.A., et al.: Strike (with) a pose: neural networks are easily fooled by strange poses of familiar objects. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019
Azulay, A., Weiss, Y.: Why do deep convolutional networks generalize so poorly to small image transformations? J. Mach. Learn. Res. (JMLR) 20(184), 1–25 (2019)
Che, Z., et al.: D2-city: a large-scale dashcam video dataset of diverse traffic scenarios. arXiv preprint arXiv:1904.01975 (2019)
Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation strategies from data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 113–123 (2019)
Dumont, B., Maggio, S., Montalvo, P.: Robustness of rotation-equivariant networks to adversarial perturbations. arXiv preprint arXiv:1802.06627 (2018)
Dvornik, N., Mairal, J., Schmid, C.: Modeling visual context is key to augmenting object detection datasets. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 375–391. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01258-8_23
Dwibedi, D., Misra, I., Hebert, M.: Cut, paste and learn: Surprisingly easy synthesis for instance detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1301–1310 (2017)
Engstrom, L., Tran, B., Tsipras, D., Schmidt, L., Madry, A.: Exploring the landscape of spatial robustness. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the International Conference on Machine Learning (ICML), vol. 97, pp. 1802–1811. PMLR, Long Beach, California, USA, 09–15 June 2019
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge 2012 (VOC2012) Results. http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html
Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: Imagenet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In: Proceedings of the International Conference on Learning Representations (ICLR) (2019)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems (NeurIPS) (2014)
Hamdi, A., Ghanem, B.: Towards analyzing semantic robustness of deep neural networks. In: Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCV Workshops) (2019)
Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: Proceedings of the International Conference on Learning Representations (ICLR) (2019)
Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. arXiv preprint arXiv:1907.07174 (2019)
Hosseini, H., Poovendran, R.: Semantic adversarial examples. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), pp. 1614–1619 (2018)
Jakab, T., Gupta, A., Bilen, H., Vedaldi, A.: Unsupervised learning of object landmarks through conditional image generation. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems (NeurIPS), pp. 4016–4027. Curran Associates, Inc. (2018)
Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. In: Proceedings of the International Conference on Learning Representations (ICLR) (2016)
Li, Y.J., Lin, C.S., Lin, Y.B., Wang, Y.C.F.: Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 7919–7929 (2019)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Liu, H.T.D., Tao, M., Li, C.L., Nowrouzezahrai, D., Jacobson, A.: Beyond pixel norm-balls: parametric adversaries using an analytically differentiable renderer. In: Proceedings of the International Conference on Learning Representations (ICLR) (2019)
Lorenz, D., Bereska, L., Milbich, T., Ommer, B.: Unsupervised part-based disentangling of object shape and appearance. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10947–10956 (2019)
Maddison, C.J., Mnih, A., Teh, Y.W.: The concrete distribution: a continuous relaxation of discrete random variables (2016)
Michaelis, C., et al.: Benchmarking robustness in object detection: autonomous driving when winter is coming. arXiv preprint arXiv:1907.07484 (2019)
Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Peyre, J., Laptev, I., Schmid, C., Sivic, J.: Weakly-supervised learning of visual relations. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)
Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do cifar-10 classifiers generalize to cifar-10? arXiv preprint arXiv:1806.00451 (2018)
Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do ImageNet classifiers generalize to ImageNet? In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the International Conference on Machine Learning (ICML), vol. 97, pp. 5389–5400. PMLR, Long Beach, California, USA, 09–15 June 2019
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Rosenfeld, A., Zemel, R., Tsotsos, J.K.: The elephant in the room. arXiv preprint arXiv:1808.03305 (2018)
Shankar, V., Dave, A., Roelofs, R., Ramanan, D., Recht, B., Schmidt, L.: A systematic framework for natural perturbations from videos. In: Proceedings of the International Conference on Machine Learning Workshops (ICML Workshop) (2019)
Shetty, R., Fritz, M., Schiele, B.: Adversarial scene editing: automatic object removal from weak supervision. In: Advances in Neural Information Processing Systems (NeurIPS) (2018)
Shetty, R., Schiele, B., Fritz, M.: Not using the car to see the sidewalk-quantifying and controlling the effects of context in classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8218–8226 (2019)
Siarohin, A., Lathuilière, S., Tulyakov, S., Ricci, E., Sebe, N.: Animating arbitrary objects via deep motion transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2372–2381 (2019)
Song, Y., Shu, R., Kushman, N., Ermon, S.: Constructing unrestricted adversarial examples with generative models. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R., (eds.) Advances in Neural Information Processing Systems (NeurIPS), pp. 8312–8323. Curran Associates, Inc. (2018)
Stutz, D., Hein, M., Schiele, B.: Disentangling adversarial robustness and generalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6976–6987 (2019)
Tripathi, S., Chandra, S., Agrawal, A., Tyagi, A., Rehg, J.M., Chari, V.: Learning to generate synthetic data via compositing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 461–470 (2019)
Ultralytics: pytorch implementation of YoloV3 (2019). https://github.com/ultralytics/yolov3. Accessed 11 Nov 2019
Wang, H.: Implentation of data augmentation for object detection via progressive and selective instance-switching (2019). https://github.com/Hwang64/PSIS. Accessed 11 Nov 2019
Wang, H., Wang, Q., Yang, F., Zhang, W., Zuo, W.: Data augmentation for object detection via progressive and selective instance-switching. arXiv preprint arXiv:1906.00358 (2019)
Wang, X., Shrivastava, A., Gupta, A.: A-fast-RCNN: hard positive generation via adversary for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2606–2615 (2017)
Xiao, C., Zhu, J.Y., Li, B., He, W., Liu, M., Song, D.: Spatially transformed adversarial examples. In: Proceedings of the International Conference on Learning Representations (ICLR) (2018)
Yu, F., et al.: BDD100k: a diverse driving dataset for heterogeneous multitask learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2636–2645 (2020)
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Shetty, R., Fritz, M., Schiele, B. (2020). Towards Automated Testing and Robustification by Semantic Adversarial Data Generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12347. Springer, Cham. https://doi.org/10.1007/978-3-030-58536-5_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-58536-5_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58535-8
Online ISBN: 978-3-030-58536-5
eBook Packages: Computer ScienceComputer Science (R0)