Full search page →

Receptive fields through upsampling and skips

Optional · supplementary note 3 of 5 for DLCV 01B · Building Blocks and How to Compose Them: Classification and Restoration Networks. 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 · 5

  1. CBAM’s channel and spatial gates
  2. Phase sums of a transposed convolution in 1-D
  3. Receptive fields through upsampling and skips
  4. The ConvNeXt roadmap step by step
  5. RegNet’s quantized linear widths

Paper guides · 4

  1. Simple Baselines for Image Restoration (NAFNet)
  2. Designing Network Design Spaces (RegNet)
  3. A Comparative Study of Image Restoration Networks for General Backbone Network Design (X-Restormer)
  4. RepVGG: training with branches, deploying a plain network

Deep Learning for Computer Vision

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

This note explains the backward interval method used by the receptive-field snippet, and when it is exact.

The question. For one output unit at position pp of the last layer, which input positions can change its value? For a chain of layers, answer it backward: start with the interval [p,p][p, p] at the output and map it through each layer, from the last to the first, to the interval of positions in that layer’s input that feed it.

Convolution. A layer with kernel size kk, stride ss and padding q=⌊(k−1)/2⌋q = \lfloor (k - 1)/2 \rfloor computes output unit uu from inputs su−q,…,su−q+k−1s u - q, \dots, s u - q + k - 1. An interval [ℓ,h][\ell, h] of outputs therefore depends on the inputs

[ sℓ−q,    sh−q+k−1 ],[\,s\ell - q,\;\; s h - q + k - 1\,],

where ℓ\ell and hh are the first and last output positions and the new endpoints are the first input of unit ℓ\ell and the last input of unit hh. Positions outside the image stand for padding; they do not limit the interval, so the result is the theoretical receptive field away from borders.

Nearest-neighbor upsampling by ff. Output unit uu copies input unit ⌊u/f⌋\lfloor u / f \rfloor, so [ℓ,h][\ell, h] maps to [⌊ℓ/f⌋,⌊h/f⌋][\lfloor \ell / f \rfloor, \lfloor h / f \rfloor]. Because of the floor, the size of the result depends on where ℓ\ell falls relative to the blocks of ff copies: two neighboring output units can have receptive fields that differ by up to one input unit of that layer, which can be many pixels deep in a network. That is why the snippet takes the maximum over 16 consecutive output positions, a full period of a 4-level U-Net.

Skips. At a merge (addition or concatenation) the input interval is the union of the intervals through the two branches. In a U-Net, the branch through the deeper level passes through the same encoder output and then through more layers; with nearest-neighbor upsampling and a stride-2 downsampling whose window contains its own position, the deeper branch’s interval contains the skip branch’s interval. So the union equals the deepest path, and the snippet can list that path alone. The brute-force check mentioned in the main text built the U-Net in 1-D with positive weights, pushed a unit impulse from every nearby input position through it, and recorded which ones reached a given output; it found the same 206 pixels.

Edge cases. Dilated convolutions make the dependence set a lattice with holes, not an interval, so the interval method reports the span but not the gaps (see the gridding note in DLCV 04). Attention layers with global reach make the receptive field the whole input after one layer; window attention lets each token see its own M×MM \times M window, so one layer adds at most M−1M - 1 tokens of reach, and the shifted windows of the next layer carry it across window borders. Araujo, Norris and Sim give closed-form expressions for receptive field size, stride and offset in general networks, including how to handle multiple paths [53].

References

  1. K. He, X. Zhang, S. Ren and J. Sun, “Deep Residual Learning for Image Recognition,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. CVF · arXiv

  2. Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell and S. Xie, “A ConvNet for the 2020s,” in Proc. IEEE/CVF CVPR, 2022. CVF · arXiv

  3. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer et al., “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,” in International Conference on Learning Representations (ICLR), 2021. arXiv

  4. J. Liang, J. Cao, G. Sun, K. Zhang, L. Van Gool and R. Timofte, “SwinIR: Image Restoration Using Swin Transformer,” in Proc. IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021. CVF · arXiv

  5. T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan and S. Belongie, “Feature Pyramid Networks for Object Detection,” in Proc. IEEE CVPR, 2017. CVF · arXiv

  6. Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin and B. Guo, “Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows,” in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), 2021. CVF · arXiv

  7. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy et al., “ImageNet Large Scale Visual Recognition Challenge,” International Journal of Computer Vision, vol. 115, no. 3, pp. 211–252, 2015. doi

  8. W. Yu, M. Luo, P. Zhou, C. Si, Y. Zhou, X. Wang, J. Feng and S. Yan, “MetaFormer Is Actually What You Need for Vision,” in Proc. IEEE/CVF CVPR, 2022. CVF · arXiv

  9. A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto and H. Adam, “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” arXiv:1704.04861, 2017. arXiv

  10. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov and L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” in Proc. IEEE/CVF CVPR, 2018. CVF · arXiv

  11. K. He, X. Zhang, S. Ren and J. Sun, “Identity Mappings in Deep Residual Networks,” in Proc. European Conference on Computer Vision (ECCV), LNCS, Springer, 2016. doi · arXiv

  12. B. Lim, S. Son, H. Kim, S. Nah and K. M. Lee, “Enhanced Deep Residual Networks for Single Image Super-Resolution,” in Proc. IEEE CVPR Workshops (CVPRW), 2017. CVF · arXiv

  13. H. Touvron, M. Cord, A. Sablayrolles, G. Synnaeve and H. Jégou, “Going Deeper With Image Transformers,” in Proc. IEEE/CVF ICCV, 2021. CVF

  14. L. Chen, X. Chu, X. Zhang and J. Sun, NAFNet official implementation, basicsr/models/archs/NAFNet_arch.py, GitHub (megvii-research/NAFNet), accessed 2026. code

  15. Y. Zhang, K. Li, K. Li, L. Wang, B. Zhong and Y. Fu, “Image Super-Resolution Using Very Deep Residual Channel Attention Networks,” in Proc. ECCV, 2018. CVF · arXiv

  16. I. Radosavovic, R. P. Kosaraju, R. Girshick, K. He and P. Dollár, “Designing Network Design Spaces,” in Proc. IEEE/CVF CVPR, 2020. CVF · arXiv

  17. J. Hu, L. Shen and G. Sun, “Squeeze-and-Excitation Networks,” in Proc. IEEE/CVF CVPR, 2018. CVF · arXiv

  18. S. Woo, J. Park, J.-Y. Lee and I. S. Kweon, “CBAM: Convolutional Block Attention Module,” in Proc. ECCV, 2018. CVF · arXiv

  19. L. Chen, X. Chu, X. Zhang and J. Sun, “Simple Baselines for Image Restoration,” in Proc. ECCV, LNCS, Springer, 2022. doi · arXiv

  20. M.-H. Guo, T.-X. Xu, J.-J. Liu, Z.-N. Liu, P.-T. Jiang, T.-J. Mu, S.-H. Zhang, R. R. Martin, M.-M. Cheng and S.-M. Hu, “Attention Mechanisms in Computer Vision: A Survey,” Computational Visual Media, vol. 8, no. 3, pp. 331–368, 2022. doi · arXiv

  21. S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan and M.-H. Yang, “Restormer: Efficient Transformer for High-Resolution Image Restoration,” in Proc. IEEE/CVF CVPR, 2022. CVF · arXiv

  22. X. Chen, Z. Li, Y. Pu, Y. Liu, J. Zhou, Y. Qiao and C. Dong, “A Comparative Study of Image Restoration Networks for General Backbone Network Design,” in Proc. ECCV 2024, LNCS, Springer, 2025. doi · arXiv

  23. S. Ioffe and C. Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” in Proc. International Conference on Machine Learning (ICML), PMLR 37, 2015. PMLR

  24. J. L. Ba, J. R. Kiros and G. E. Hinton, “Layer Normalization,” arXiv:1607.06450, 2016. arXiv

  25. D. Ulyanov, A. Vedaldi and V. Lempitsky, “Instance Normalization: The Missing Ingredient for Fast Stylization,” arXiv:1607.08022, 2016. arXiv

  26. Y. Wu and K. He, “Group Normalization,” in Proc. ECCV, 2018. CVF · arXiv

  27. C. Ledig, L. Theis, F. Huszár, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang and W. Shi, “Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network,” in Proc. IEEE CVPR, 2017. CVF

  28. X. Wang, K. Yu, S. Wu, J. Gu, Y. Liu, C. Dong, Y. Qiao and C. C. Loy, “ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks,” in Proc. ECCV Workshops, 2018. CVF · arXiv

  29. K. Zhang, W. Zuo, Y. Chen, D. Meng and L. Zhang, “Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising,” IEEE Transactions on Image Processing, vol. 26, no. 7, pp. 3142–3155, 2017. doi · arXiv

  30. Q. Huynh-Thu and M. Ghanbari, “Scope of Validity of PSNR in Image/Video Quality Assessment,” Electronics Letters, vol. 44, no. 13, pp. 800–801, 2008. doi

  31. A. Abdelhamed, S. Lin and M. S. Brown, “A High-Quality Denoising Dataset for Smartphone Cameras,” in Proc. IEEE/CVF CVPR, 2018. CVF

  32. S. Nah, T. H. Kim and K. M. Lee, “Deep Multi-Scale Convolutional Neural Network for Dynamic Scene Deblurring,” in Proc. IEEE CVPR, 2017. CVF

  33. N. Shazeer, “GLU Variants Improve Transformer,” arXiv:2002.05202, 2020. arXiv

  34. Y. N. Dauphin, A. Fan, M. Auli and D. Grangier, “Language Modeling with Gated Convolutional Networks,” in Proc. ICML, PMLR 70, 2017. PMLR

  35. D. Hendrycks and K. Gimpel, “Gaussian Error Linear Units (GELUs),” arXiv:1606.08415, 2016. arXiv

  36. W. Shi, J. Caballero, F. Huszár, J. Totz, A. P. Aitken, R. Bishop, D. Rueckert and Z. Wang, “Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network,” in Proc. IEEE CVPR, 2016. CVF · arXiv

  37. A. Odena, V. Dumoulin and C. Olah, “Deconvolution and Checkerboard Artifacts,” Distill, vol. 1, no. 10, 2016. Distill · doi

  38. A. Aitken, C. Ledig, L. Theis, J. Caballero, Z. Wang and W. Shi, “Checkerboard Artifact Free Sub-Pixel Convolution: A Note on Sub-Pixel Convolution, Resize Convolution and Convolution Resize,” arXiv:1707.02937, 2017. arXiv

  39. O. Ronneberger, P. Fischer and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” in Proc. Medical Image Computing and Computer-Assisted Intervention (MICCAI), LNCS, Springer, pp. 234–241, 2015. doi · arXiv

  40. G. Huang, Z. Liu, L. van der Maaten and K. Q. Weinberger, “Densely Connected Convolutional Networks,” in Proc. IEEE CVPR, 2017. CVF

  41. 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, pp. 834–848, 2018. doi · arXiv

  42. W. Luo, Y. Li, R. Urtasun and R. Zemel, “Understanding the Effective Receptive Field in Deep Convolutional Neural Networks,” in Advances in Neural Information Processing Systems (NeurIPS), 2016. NeurIPS · arXiv

  43. J. Kim, J. K. Lee and K. M. Lee, “Accurate Image Super-Resolution Using Very Deep Convolutional Networks,” in Proc. IEEE CVPR, 2016. CVF · arXiv

  44. H. Guo, J. Li, T. Dai, Z. Ouyang, X. Ren and S.-T. Xia, “MambaIR: A Simple Baseline for Image Restoration with State-Space Model,” in Proc. ECCV 2024, LNCS, Springer, 2025. doi · arXiv

  45. ITU-T, “Recommendation T.81: Information technology – Digital compression and coding of continuous-tone still images – Requirements and guidelines” (the JPEG standard), 1992. ITU

  46. T. Elsken, J. H. Metzen and F. Hutter, “Neural Architecture Search: A Survey,” Journal of Machine Learning Research, vol. 20, 2019. JMLR · arXiv

  47. A. Khan, A. Sohail, U. Zahoora and A. S. Qureshi, “A Survey of the Recent Architectures of Deep Convolutional Neural Networks,” Artificial Intelligence Review, vol. 53, no. 8, pp. 5455–5516, 2020. doi · arXiv

  48. S. Khan, M. Naseer, M. Hayat, S. W. Zamir, F. S. Khan and M. Shah, “Transformers in Vision: A Survey,” ACM Computing Surveys, vol. 54, no. 10s, 2022. doi · arXiv

  49. S. Woo, S. Debnath, R. Hu, X. Chen, Z. Liu, I. S. Kweon and S. Xie, “ConvNeXt V2: Co-Designing and Scaling ConvNets With Masked Autoencoders,” in Proc. IEEE/CVF CVPR, 2023. CVF · arXiv

  50. M. Goldblum, H. Souri, R. Ni, M. Shu, V. Prabhu, G. Somepalli, P. Chattopadhyay, M. Ibrahim et al., “Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks,” in Advances in Neural Information Processing Systems (NeurIPS), 2023. arXiv

  51. X. Chen, X. Wang, J. Zhou, Y. Qiao and C. Dong, “Activating More Pixels in Image Super-Resolution Transformer,” in Proc. IEEE/CVF CVPR, 2023. CVF · arXiv

  52. H. Guo, Y. Guo, Y. Zha, Y. Zhang, W. Li, T. Dai, S.-T. Xia and Y. Li, “MambaIRv2: Attentive State Space Restoration,” in Proc. IEEE/CVF CVPR, 2025. CVF · arXiv

  53. A. Araujo, W. Norris and J. Sim, “Computing Receptive Fields of Convolutional Neural Networks,” Distill, vol. 4, no. 11, 2019. Distill · doi

  54. X. Ding, X. Zhang, N. Ma, J. Han, G. Ding and J. Sun, “RepVGG: Making VGG-style ConvNets Great Again,” in Proc. IEEE/CVF CVPR, pp. 13733–13742, 2021. CVF paper

  55. S. Zagoruyko and N. Komodakis, “DiracNets: Training Very Deep Neural Networks Without Skip-Connections,” arXiv:1706.00388, 2017. arXiv

  56. X. Ding, Y. Guo, G. Ding and J. Han, “ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks,” in Proc. IEEE/CVF ICCV, 2019. CVF

  57. H. Zhao, J. Shi, X. Qi, X. Wang and J. Jia, “Pyramid Scene Parsing Network,” in Proc. IEEE CVPR, 2017. CVF

  58. 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 CVPR, 2016. CVF

  59. E. D. Cubuk, B. Zoph, D. Mane, V. Vasudevan and Q. V. Le, “AutoAugment: Learning Augmentation Strategies From Data,” in Proc. IEEE/CVF CVPR, 2019. CVF

  60. H. Zhang, M. Cisse, Y. N. Dauphin and D. Lopez-Paz, “mixup: Beyond Empirical Risk Minimization,” in Proc. ICLR, 2018. arXiv