# Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects

arXiv: https://arxiv.org/abs/1811.11553 · HTML: https://mlsanity.com/paper/1811.11553/

## Key facts

- Cited by 143 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2018.

## Built on by (most cited first, 30 of 143)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Partial success in closing the gap between human and machine vision](https://mlsanity.com/paper/2106.07411/) (2021)
- [Simple data balancing achieves competitive worst-group-accuracy](https://mlsanity.com/paper/2110.14503/) (2021)
- [A Fine-Grained Analysis on Distribution Shift](https://mlsanity.com/paper/2110.11328/) (2021)
- [On Feature Learning in the Presence of Spurious Correlations](https://mlsanity.com/paper/2210.11369/) (2022)
- [Counterfactual Generative Networks](https://mlsanity.com/paper/2101.06046/) (2021)
- [Abstraction and Analogy-Making in Artificial Intelligence](https://mlsanity.com/paper/2102.10717/) (2021)
- [The effectiveness of feature attribution methods and its correlation with automatic evaluation scores](https://mlsanity.com/paper/2105.14944/) (2021)
- [OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization](https://mlsanity.com/paper/2106.03721/) (2021)
- [MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets](https://mlsanity.com/paper/2109.05184/) (2021)
- [NICO++: Towards Better Benchmarking for Domain Generalization](https://mlsanity.com/paper/2204.08040/) (2022)
- [Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision](https://mlsanity.com/paper/2202.08360/) (2022)
- [Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering](https://mlsanity.com/paper/2104.03149/) (2021)
- [Understanding Softmax Confidence and Uncertainty](https://mlsanity.com/paper/2106.04972/) (2021)
- [A Comprehensive Survey of Foundation Models in Medicine](https://mlsanity.com/paper/2406.10729/) (2024)
- [ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints](https://mlsanity.com/paper/2210.03895/) (2022)
- [OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images](https://mlsanity.com/paper/2111.14341/) (2021)
- [ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations](https://mlsanity.com/paper/2211.01866/) (2022)
- [Visual correspondence-based explanations improve AI robustness and human-AI team accuracy](https://mlsanity.com/paper/2208.00780/) (2022)
- [Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation](https://mlsanity.com/paper/2302.07865/) (2023)
- [ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification](https://mlsanity.com/paper/2304.05538/) (2023)
- [3DB: A Framework for Debugging Computer Vision Models](https://mlsanity.com/paper/2106.03805/) (2021)
- [PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning](https://mlsanity.com/paper/2308.03977/) (2023)
- [Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation](https://mlsanity.com/paper/2508.06426/) (2025)
- [Linear unit-tests for invariance discovery](https://mlsanity.com/paper/2102.10867/) (2021)
- [Grounding inductive biases in natural images:invariance stems from variations in data](https://mlsanity.com/paper/2106.05121/) (2021)

## Abstract (arXiv)

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.