Flip testing and left–right bookkeeping
Optional · supplementary note 3 of 5 for DLCV 05 · Human Pose and Keypoint Estimation. Nothing in the main text depends on it; citation numbers refer to the reference list at the bottom of this page.
Navigate: this page and this track: Navigate: this page and this track
This note works through the index arithmetic of mirroring heatmaps, the step that flip augmentation and flip testing share.
Mirroring the image. For a crop of width pixels, a horizontal flip maps an image column to (with pixel centres at integer coordinates). Keypoint coordinates are transformed the same way: , with unchanged.
Swapping the labels. After mirroring, the person’s left side appears where the right side was. Let be the permutation that exchanges each left keypoint with its right twin (left eye with right eye, left shoulder with right shoulder, and so on) and leaves the nose unchanged. A flipped training sample must use the label of keypoint for channel ; otherwise the network is trained to call the person’s right wrist “left” in half of the images, and it learns to hedge between the two.
Flip testing. Given heatmaps for the crop and for its mirror image, the averaged map for channel is
where is the heatmap width and is a heatmap cell. Two operations happen: the mirrored map is flipped back column-wise, and its channels are permuted with .
A subtle offset. The column mapping is exact only if heatmap cells and image pixels are aligned the same way after flipping. With stride and image width , suppose cell stands for image position (its first pixel). Flipping the image sends that position to , but the flipped cell stands for . The two differ by pixels, so averaging the two maps biases every keypoint by about pixels. If instead cell stands for the centre of the pixels it covers, , the flipped cell stands for , exactly the flipped position, and the bias disappears. Whatever convention a codebase uses, test it with a synthetic heatmap: flip-test a perfect Gaussian and check that the decoded position does not move.
What goes wrong without the swap. Exercise 6 shows that forgetting in flip testing averages a left-wrist blob with a right-wrist blob, which produces inversion errors. In augmentation the same mistake is quieter: it does not crash and only lowers accuracy, so it is a classic silent bug.
References
- A. Mathis, P. Mamidanna, K. M. Cury, T. Abe, V. N. Murthy, M. W. Mathis and M. Bethge, “DeepLabCut: Markerless pose estimation of user-defined body parts with deep learning,” Nature Neuroscience, vol. 21, no. 9, 2018. doi · arXiv
- C. Zheng, W. Wu, C. Chen, T. Yang, S. Zhu, J. Shen, N. Kehtarnavaz and M. Shah, “Deep learning-based human pose estimation: A survey,” ACM Computing Surveys, vol. 56, no. 1, 2024. doi · arXiv
- Y. Chen, Y. Tian and M. He, “Monocular human pose estimation: A survey of deep learning-based methods,” Computer Vision and Image Understanding, vol. 192, 102897, 2020. doi · arXiv
- COCO Consortium, “Keypoint evaluation,” COCO dataset official documentation (accessed 2026-11-01). cocodataset.org
- Y. Tian, H. Zhang, Y. Liu and L. Wang, “Recovering 3D human mesh from monocular images: A survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 12, 2023. doi · arXiv
- A. Toshev and C. Szegedy, “DeepPose: Human pose estimation via deep neural networks,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. doi · arXiv
- J. Tompson, A. Jain, Y. LeCun and C. Bregler, “Joint training of a convolutional network and a graphical model for human pose estimation,” in Advances in Neural Information Processing Systems (NeurIPS), 2014. NeurIPS · arXiv
- A. Newell, K. Yang and J. Deng, “Stacked hourglass networks for human pose estimation,” in Proc. European Conference on Computer Vision (ECCV), LNCS, 2016. doi · arXiv
- B. Xiao, H. Wu and Y. Wei, “Simple baselines for human pose estimation and tracking,” in Proc. European Conference on Computer Vision (ECCV), LNCS, 2018. doi · arXiv
- F. Zhang, X. Zhu, H. Dai, M. Ye and C. Zhu, “Distribution-aware coordinate representation for human pose estimation,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. doi · arXiv
- X. Sun, B. Xiao, F. Wei, S. Liang and Y. Wei, “Integral human pose regression,” in Proc. European Conference on Computer Vision (ECCV), LNCS, 2018. doi · arXiv
- Y. Li, S. Yang, P. Liu, S. Zhang, Y. Wang, Z. Wang, W. Yang and S.-T. Xia, “SimCC: A simple coordinate classification perspective for human pose estimation,” in Proc. European Conference on Computer Vision (ECCV), LNCS, 2022. doi · arXiv
- J. Li, S. Bian, A. Zeng, C. Wang, B. Pang, W. Liu and C. Lu, “Human pose regression with residual log-likelihood estimation,” in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), 2021. doi · arXiv
- S.-E. Wei, V. Ramakrishna, T. Kanade and Y. Sheikh, “Convolutional pose machines,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. doi · arXiv
- K. Sun, B. Xiao, D. Liu and J. Wang, “Deep high-resolution representation learning for human pose estimation,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019. doi · arXiv
- Y. Xu, J. Zhang, Q. Zhang and D. Tao, “ViTPose: Simple vision transformer baselines for human pose estimation,” in Advances in Neural Information Processing Systems (NeurIPS), 2022. NeurIPS · arXiv
- K. He, G. Gkioxari, P. Dollár and R. Girshick, “Mask R-CNN,” in Proc. IEEE International Conference on Computer Vision (ICCV), 2017. doi · arXiv
- Z. Cao, T. Simon, S.-E. Wei and Y. Sheikh, “Realtime multi-person 2D pose estimation using part affinity fields,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. doi · arXiv
- A. Newell, Z. Huang and J. Deng, “Associative embedding: End-to-end learning for joint detection and grouping,” in Advances in Neural Information Processing Systems (NeurIPS), 2017. NeurIPS · arXiv
- B. Cheng, B. Xiao, J. Wang, H. Shi, T. S. Huang and L. Zhang, “HigherHRNet: Scale-aware representation learning for bottom-up human pose estimation,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. doi · arXiv
- Z. Geng, K. Sun, B. Xiao, Z. Zhang and J. Wang, “Bottom-up human pose estimation via disentangled keypoint regression,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021. doi · arXiv
- X. Zhou, D. Wang and P. Krähenbühl, “Objects as points,” arXiv:1904.07850, 2019. arXiv
- P. Lu, T. Jiang, Y. Li, X. Li, K. Chen and W. Yang, “RTMO: Towards high-performance one-stage real-time multi-person pose estimation,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. doi · arXiv
- J. Yang, A. Zeng, S. Liu, F. Li, R. Zhang and L. Zhang, “Explicit box detection unifies end-to-end multi-person pose estimation,” in Proc. International Conference on Learning Representations (ICLR), 2023. OpenReview · arXiv
- Y. Yang and D. Ramanan, “Articulated human detection with flexible mixtures of parts,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 12, 2013. doi
- M. Andriluka, L. Pishchulin, P. Gehler and B. Schiele, “2D human pose estimation: New benchmark and state of the art analysis,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. doi · CVF
- COCO Consortium,
cocoeval.py(keypoint OKS computation and the per-keypoint sigmas), official COCO API source code (accessed 2026-11-01). GitHub - J. Martinez, R. Hossain, J. Romero and J. J. Little, “A simple yet effective baseline for 3d human pose estimation,” in Proc. IEEE International Conference on Computer Vision (ICCV), 2017. doi · arXiv
- M. R. Ronchi and P. Perona, “Benchmarking and error diagnosis in multi-instance pose estimation,” in Proc. IEEE International Conference on Computer Vision (ICCV), 2017. doi · arXiv
- T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár and C. L. Zitnick, “Microsoft COCO: Common objects in context,” in Proc. European Conference on Computer Vision (ECCV), LNCS, 2014. doi · arXiv
- J. Li, C. Wang, H. Zhu, Y. Mao, H.-S. Fang and C. Lu, “CrowdPose: Efficient crowded scenes pose estimation and a new benchmark,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019. doi · arXiv
- S. Jin, L. Xu, J. Xu, C. Wang, W. Liu, C. Qian, W. Ouyang and P. Luo, “Whole-body human pose estimation in the wild,” in Proc. European Conference on Computer Vision (ECCV), LNCS, 2020. doi · arXiv
- M. Andriluka, U. Iqbal, E. Insafutdinov, L. Pishchulin, A. Milan, J. Gall and B. Schiele, “PoseTrack: A benchmark for human pose estimation and tracking,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018. doi · arXiv
- C. Ionescu, D. Papava, V. Olaru and C. Sminchisescu, “Human3.6M: Large scale datasets and predictive methods for 3D human sensing in natural environments,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 7, 2014. doi · project page
- H. Yu, Y. Xu, J. Zhang, W. Zhao, Z. Guan and D. Tao, “AP-10K: A benchmark for animal pose estimation in the wild,” in Advances in Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, 2021. NeurIPS · arXiv
- Z. Cao, G. Hidalgo, T. Simon, S.-E. Wei and Y. Sheikh, “OpenPose: Realtime multi-person 2D pose estimation using part affinity fields,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 1, 2021. doi · arXiv
- D. Pavllo, C. Feichtenhofer, D. Grangier and M. Auli, “3D human pose estimation in video with temporal convolutions and semi-supervised training,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019. doi · arXiv
- K. Iskakov, E. Burkov, V. Lempitsky and Y. Malkov, “Learnable triangulation of human pose,” in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), 2019. doi · arXiv
- M. Loper, N. Mahmood, J. Romero, G. Pons-Moll and M. J. Black, “SMPL: A skinned multi-person linear model,” ACM Transactions on Graphics (Proc. SIGGRAPH Asia), vol. 34, no. 6, 2015. doi
- A. Kanazawa, M. J. Black, D. W. Jacobs and J. Malik, “End-to-end recovery of human shape and pose,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018. doi · arXiv
- S. Goel, G. Pavlakos, J. Rajasegaran, A. Kanazawa and J. Malik, “Humans in 4D: Reconstructing and tracking humans with transformers,” in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), 2023. doi · arXiv
- R. Khirodkar, T. Bagautdinov, J. Martinez, S. Zhaoen, A. James, P. Selednik, S. Anderson and S. Saito, “Sapiens: Foundation for human vision models,” in Proc. European Conference on Computer Vision (ECCV), LNCS, 2024. doi · arXiv
- T. Jiang, P. Lu, L. Zhang, N. Ma, R. Han, C. Lyu, Y. Li and K. Chen, “RTMPose: Real-time multi-person pose estimation based on MMPose,” arXiv:2303.07399, 2023. arXiv