Full search page →

Gridding in stacked dilated convolutions

Optional · supplementary note 1 of 4 for DLCV 04 · Image Segmentation: Semantic, Instance and Panoptic. 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

On this page

Supplementary notes · 4

  1. Gridding in stacked dilated convolutions
  2. Dense CRF post-processing
  3. The gradient of the soft Dice loss
  4. Boundary IoU in detail

Paper guides · 2

  1. Panoptic Segmentation: a reading guide
  2. Mask2Former: a reading guide

Deep Learning for Computer Vision

  1. 02 · Deep Image Classification
View the whole course tree →

This note explains which sequences of dilation rates leave holes in the receptive field, and a simple rule for choosing rates that do not.

The problem. Take one output of a stack of nn dilated convolutions with kernel size kk and rates r1,…,rnr_1, \dots, r_n, and ask which input positions influence it. In 1-D, the set of reachable offsets is the sum set {∑lrldl:dl∈{−c,…,c}}\{\sum_l r_l d_l : d_l \in \{-c, \dots, c\}\} with c=(k−1)/2c = (k - 1)/2. If every rlr_l is a multiple of some integer q>1q \gt 1, every reachable offset is a multiple of qq as well: the output sees one input in qq along each axis, a regular lattice with holes. Neighbouring outputs then read disjoint lattices, and the output map shows a checkerboard pattern. Wang et al. [11] call this gridding and note that it gets worse at high rates, where a sparse kernel no longer covers any local neighbourhood.

The rule. Their hybrid dilated convolution (HDC) uses different rates in consecutive layers, arranged in a sawtooth pattern, chosen so that the final receptive field covers a square region without holes. Define the maximum distance between two nonzero taps seen through layers ii to nn recursively as

Mi=max⁡[Mi+1−2ri,  Mi+1−2(Mi+1−ri),  ri],Mn=rn,M_i = \max\big[M_{i+1} - 2 r_i,\; M_{i+1} - 2(M_{i+1} - r_i),\; r_i\big], \qquad M_n = r_n,

where rir_i is the rate of layer ii. The design goal is M2≤kM_2 \le k. For k=3k = 3, rates (1,2,5)(1, 2, 5) give M2=2M_2 = 2 and work, while (1,2,9)(1, 2, 9) give M2=5M_2 = 5 and do not [11]. They also state that the rates within a group should not have a common factor such as 2, 4, 8.

A check in code. Counting the paths from each input offset to one output makes the holes visible.

Code · Python · 13 lines
import numpy as np

def coverage(rates, k=3):
    """How many paths connect each input offset to one output of a stack of 1-D dilated convs."""
    reach = np.array([1])
    for r in rates:
        taps = np.zeros(r * (k - 1) + 1, int); taps[::r] = 1      # a k-tap kernel with rate r
        reach = np.convolve(reach, taps)
    return reach

for rates in [(2, 2, 2), (1, 2, 4), (1, 2, 5), (1, 2, 9)]:
    c = coverage(rates)
    print(f"rates {rates}: span {len(c)}, holes {int((c == 0).sum())}, paths {c}")

Output

rates (2, 2, 2): span 13, holes 6, paths [1 0 3 0 6 0 7 0 6 0 3 0 1]
rates (1, 2, 4): span 15, holes 0, paths [1 1 2 1 3 2 3 1 3 2 3 1 2 1 1]
rates (1, 2, 5): span 17, holes 0, paths [1 1 2 1 2 2 2 2 1 2 2 2 2 1 2 1 1]
rates (1, 2, 9): span 25, holes 4, paths [1 1 2 1 2 1 1 0 0 1 1 2 1 2 1 1 0 0 1 1 2 1 2 1 1]

Equal rates of 2 leave every second input unseen; a jump from 2 to 9 leaves gaps between the copies of the inner pattern. The path counts also show that coverage is uneven even without holes: some offsets are reached by three paths, others by one.

Edge cases. ASPP is not affected in the same way, because its branches run in parallel on the same map and are combined, not stacked. And a backbone whose earlier, undilated layers already mix neighbouring pixels softens gridding in practice; the problem is strongest when several highly dilated layers follow each other.

References

  1. S. Minaee, Y. Boykov, F. Porikli, A. Plaza, N. Kehtarnavaz and D. Terzopoulos, “Image segmentation using deep learning: A survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 7, 2022. doi · arXiv
  2. X. Li, H. Ding, H. Yuan, W. Zhang, J. Pang, G. Cheng, K. Chen, Z. Liu and C. C. Loy, “Transformer-based visual segmentation: A survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 12, 2024. doi · arXiv
  3. T. Zhou, W. Xia, F. Zhang, B. Chang, W. Wang, Y. Yuan, E. Konukoglu and D. Cremers, “Image segmentation in foundation model era: A survey,” arXiv:2408.12957, 2024. arXiv
  4. A. Kirillov, K. He, R. Girshick, C. Rother and P. Dollár, “Panoptic segmentation,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019. doi · arXiv
  5. J. Long, E. Shelhamer and T. Darrell, “Fully convolutional networks for semantic segmentation,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. doi · arXiv
  6. O. Ronneberger, P. Fischer and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention (MICCAI), LNCS vol. 9351, 2015. doi
  7. L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in Proc. European Conference on Computer Vision (ECCV), 2018. doi · arXiv
  8. L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy and A. L. Yuille, “DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 4, 2018. doi · arXiv
  9. F. Yu and V. Koltun, “Multi-scale context aggregation by dilated convolutions,” in Proc. International Conference on Learning Representations (ICLR), 2016. arXiv
  10. L.-C. Chen, G. Papandreou, F. Schroff and H. Adam, “Rethinking atrous convolution for semantic image segmentation,” arXiv:1706.05587, 2017. arXiv
  11. P. Wang, P. Chen, Y. Yuan, D. Liu, Z. Huang, X. Hou and G. Cottrell, “Understanding convolution for semantic segmentation,” in Proc. IEEE Winter Conference on Applications of Computer Vision (WACV), 2018. doi · arXiv
  12. H. Zhao, J. Shi, X. Qi, X. Wang and J. Jia, “Pyramid scene parsing network,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. doi · arXiv
  13. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” in Proc. International Conference on Learning Representations (ICLR), 2021. arXiv
  14. E. Xie, W. Wang, Z. Yu, A. Anandkumar, J. M. Alvarez and P. Luo, “SegFormer: Simple and efficient design for semantic segmentation with transformers,” in Advances in Neural Information Processing Systems (NeurIPS), 2021. NeurIPS · arXiv
  15. F. Milletari, N. Navab and S.-A. Ahmadi, “V-Net: Fully convolutional neural networks for volumetric medical image segmentation,” in Proc. Fourth International Conference on 3D Vision (3DV), 2016. doi · arXiv
  16. T.-Y. Lin, P. Goyal, R. Girshick, K. He and P. Dollár, “Focal loss for dense object detection,” in Proc. IEEE International Conference on Computer Vision (ICCV), 2017. doi
  17. B. Cheng, A. G. Schwing and A. Kirillov, “Per-pixel classification is not all you need for semantic segmentation,” in Advances in Neural Information Processing Systems (NeurIPS), 2021. NeurIPS · arXiv
  18. M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth and B. Schiele, “The Cityscapes dataset for semantic urban scene understanding,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. doi · arXiv
  19. B. Cheng, R. Girshick, P. Dollár, A. C. Berg and A. Kirillov, “Boundary IoU: Improving object-centric image segmentation evaluation,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021. doi · arXiv
  20. K. He, G. Gkioxari, P. Dollár and R. Girshick, “Mask R-CNN,” in Proc. IEEE International Conference on Computer Vision (ICCV), 2017. doi · arXiv
  21. S. Ren, K. He, R. Girshick and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, 2017. doi
  22. T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan and S. Belongie, “Feature pyramid networks for object detection,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. doi
  23. A. Kirillov, Y. Wu, K. He and R. Girshick, “PointRend: Image segmentation as rendering,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. doi · arXiv
  24. A. Kirillov, R. Girshick, K. He and P. Dollár, “Panoptic feature pyramid networks,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019. doi · arXiv
  25. N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov and S. Zagoruyko, “End-to-end object detection with transformers,” in Proc. European Conference on Computer Vision (ECCV), 2020. doi · arXiv
  26. B. Cheng, I. Misra, A. G. Schwing, A. Kirillov and R. Girdhar, “Masked-attention mask transformer for universal image segmentation,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. doi · arXiv
  27. J. Jain, J. Li, M. Chiu, A. Hassani, N. Orlov and H. Shi, “OneFormer: One transformer to rule universal image segmentation,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. doi · arXiv
  28. T. Kerssies, N. Cavagnero, A. Hermans, N. Norouzi, G. Averta, B. Leibe, G. Dubbelman and D. de Geus, “Your ViT is secretly an image segmentation model,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. CVF · arXiv
  29. A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson et al., “Segment anything,” in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), 2023. doi · arXiv
  30. N. Ravi, V. Gabeur, Y.-T. Hu, R. Hu, C. Ryali, T. Ma et al., “SAM 2: Segment anything in images and videos,” in Proc. International Conference on Learning Representations (ICLR), 2025. OpenReview · arXiv
  31. N. Carion, L. Gustafson, Y.-T. Hu, S. Debnath, R. Hu, D. Suris et al., “SAM 3: Segment anything with concepts,” in Proc. International Conference on Learning Representations (ICLR), 2026. OpenReview · arXiv
  32. A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal et al., “Learning transferable visual models from natural language supervision,” in Proc. International Conference on Machine Learning (ICML), PMLR 139, 2021. PMLR
  33. B. Li, K. Q. Weinberger, S. Belongie, V. Koltun and R. Ranftl, “Language-driven semantic segmentation,” in Proc. International Conference on Learning Representations (ICLR), 2022. OpenReview · arXiv
  34. S. Cho, H. Shin, S. Hong, A. Arnab, P. H. Seo and S. Kim, “CAT-Seg: Cost aggregation for open-vocabulary semantic segmentation,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. doi · arXiv
  35. C. Zhu and L. Chen, “A survey on open-vocabulary detection and segmentation: Past, present, and future,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 12, 2024. doi
  36. M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn and A. Zisserman, “The PASCAL Visual Object Classes (VOC) challenge,” International Journal of Computer Vision, vol. 88, no. 2, 2010. doi
  37. B. Zhou, H. Zhao, X. Puig, S. Fidler, A. Barriuso and A. Torralba, “Scene parsing through ADE20K dataset,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. doi · CVF
  38. T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan et al., “Microsoft COCO: Common objects in context,” in Proc. European Conference on Computer Vision (ECCV), 2014. doi · arXiv
  39. H. Caesar, J. Uijlings and V. Ferrari, “COCO-Stuff: Thing and stuff classes in context,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018. doi · arXiv
  40. G. Neuhold, T. Ollmann, S. Rota Bulò and P. Kontschieder, “The Mapillary Vistas dataset for semantic understanding of street scenes,” in Proc. IEEE International Conference on Computer Vision (ICCV), 2017. doi
  41. P. Krähenbühl and V. Koltun, “Efficient inference in fully connected CRFs with Gaussian edge potentials,” in Advances in Neural Information Processing Systems (NeurIPS), 2011. NeurIPS · arXiv