Strike (With) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects
Open accessThe DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
Despite excellent performance on stationary test sets, deep neural networks (DNNs) can fail to generalize to out-of-distribution (OoD) inputs, including natural, non-adversarial ones, which are common in real-world settings. In this paper, we present a framework for discovering DNN failures that harnesses 3D renderers and 3D models. That is, we estimate the parameters of a 3D renderer that cause a target DNN to misbehave in response to the rendered image. Using our framework and a self-assembled dataset of 3D objects, we investigate the vulnerability of DNNs to OoD poses of well-known objects in ImageNet. For objects that are readily recognized by DNNs in their canonical poses, DNNs incorrectly classify 97% of their pose space. In addition, DNNs are highly sensitive to slight pose perturbations. Importantly, adversarial poses transfer across models and datasets. We find that 99.9% and 99.4% of the poses misclassified by Inception-v3 also transfer to the AlexNet and ResNet-50 image classifiers trained on the same ImageNet dataset, respectively, and 75.5% transfer to the YOLOv3 object detector trained on MS COCO.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
YOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687 · cited 1×
“augmenting the training set with AXs—also a common approach in anomaly detection [9].”
MethodExplaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859
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
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Nguyen, A., Yosinski, J., & Clune, J. (2014) · arXiv · doi:10.48550/arxiv.1412.1897 · Cited by 3,258
Self-citationDeep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258
Self-citation
Cited by
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
“However, research in the subsequent years has repeatedly found that these models still make many simple mistakes (Dodge & Karam, 2017; Geirhos et al., 2018; Alcorn et al., 2019), and new benchmarks testing these systems has often found their performance to be much lower than both their ImageNet accuracy and human accu…”
BackgroundShortcut learning in deep neural networks
Geirhos, R., Jacobsen, J.-H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., & Wichmann, F. A. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-00257-z · Cited by 2,224
Objaverse: A Universe of Annotated 3D Objects
Deitke, M., Schwenk, D., Salvador, J., Weihs, L., Michel, O., VanderBilt, E., Schmidt, L., Ehsanit, K., Kembhavi, A., & Farhadi, A. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01263 · Cited by 725
Robust fine-tuning of zero-shot models
Wortsman, M., Ilharco, G., Kim, J. W., Li, M., Kornblith, S., Roelofs, R., Lopes, R. G., Hajishirzi, H., Farhadi, A., Namkoong, H., et al. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00780 · Cited by 428
“…model behavior under synthetic (Hendrycks & Dietterich, 2019; Tram`er et al., 2017; Madry et al., 2017; Geirhos et al., 2018b; Eykholt et al., 2018; Alcorn et al., 2019) and natural distribution shift (Hendrycks et al., 2021a; Koh et al., 2021; Wang et al., 2019; Barbu et al., 2019; Hendrycks et…”
BackgroundInfluentialBenchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming
Michaelis, C., Mitzkus, B., Geirhos, R., Rusak, E., Bringmann, O., Ecker, A. S., Bethge, M., & Brendel, W. (2019) · arXiv · doi:10.48550/arxiv.1907.07484 · Cited by 324
The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
Marcus, G. (2020) · arXiv · doi:10.48550/arxiv.2002.06177 · Cited by 297
“ome sentences correctly but fails in the presence of unrelated distractor material. Sample of how an object in a noncanonical orientation and context fools many current object classification systems (Alcorn et al., 2018) Sample of how adversarially inserted material fools a large-scale language model (Jia & Liang,…”
BackgroundDeep problems with neural network models of human vision
Bowers, J. S., Malhotra, G., Dujmović, M., Llera Montero, M., Tsvetkov, C., Biscione, V., Puebla, G., Adolfi, F., Hummel, J. E., Heaton, R. F., et al. (2023) · Behavioral and Brain Sciences · doi:10.1017/s0140525x22002813 · Cited by 204
Artificial Intelligence in Nephrology: Core Concepts, Clinical Applications, and Perspectives
Niel, O., & Bastard, P. (2019) · American Journal of Kidney Diseases · doi:10.1053/j.ajkd.2019.05.020 · Cited by 165
Performance vs. competence in human–machine comparisons
Firestone, C. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1905334117 · Cited by 150
Partial success in closing the gap between human and machine vision
Geirhos, R., Narayanappa, K., Mitzkus, B., Thieringer, T., Bethge, M., Wichmann, F. A., & Brendel, W. (2021) · arXiv · doi:10.48550/arxiv.2106.07411 · Cited by 129
“Many OOD generalisation tests have been proposed: ImageNet-C [15] for corrupted imaes, ImageNet-Sketch [16] for sketches, Stylized-ImageNet [17] for image style changes, [18] for unfamiliar object poses, and many more [19–29].”
BackgroundAbstraction and analogy‐making in artificial intelligence
Mitchell, M. (2021) · Annals of the New York Academy of Sciences · doi:10.1111/nyas.14619 · Cited by 125
15 challenges for AI: Or what AI (currently) can’t do
Hagendorff, T., & Wezel, K. (2020) · AI & SOCIETY · doi:10.1007/s00146-019-00886-y · Cited by 113
Deep Nets: What have They Ever Done for Vision?
Yuille, A. L., & Liu, C. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01405-z · Cited by 98
In Search of Lost Domain Generalization
Gulrajani, I., & Lopez-Paz, D. (2020) · arXiv · doi:10.48550/arxiv.2007.01434 · Cited by 440
“For instance, self-driving car systems struggle to perform under conditions different to those of training, including variations in light [Dai and Van Gool, 2018], weather [Volk et al., 2019], and object poses [Alcorn et al., 2019].”
BackgroundUnderstanding How Blind Users Handle Object Recognition Errors: Strategies and Challenges
Hong, J., & Kacorri, H. (2024) · The 26th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663548.3675635 · Cited by 14
Ahmed, F., & Courville, A. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.5712 · Cited by 5
Certifying Model Accuracy under Distribution Shifts
Kumar, A., Levine, A., Goldstein, T., & Feizi, S. (2022) · arXiv · doi:10.48550/arxiv.2201.12440 · Cited by 3
Metadata
- Authors
- Alcorn, M. A., Li, Q., Gong, Z., Wang, C., Mai, L., Ku, W.-S., & Nguyen, A.
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 4840-4849
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2903037999
- Cited by
- 250
- References
- 20
- FWCI
- 16.13
- Type
- conference paper
- Language
- en
- Open access
- green
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.