Full search page →

Designing Network Design Spaces (RegNet)

Optional · paper guide 2 of 4 for DLCV 01B · Building Blocks and How to Compose Them: Classification and Restoration Networks. 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 →

Challenge

Radosavovic et al. [16] ask how to make an entire family of networks easy to describe and likely to perform well. Searching for one winning model does not reveal whether nearby designs are reliable. RegNet therefore studies distributions of sampled architectures, rather than treating one selected benchmark winner as the whole argument.

Method

The left diagram defines a network family through stages and blocks; the right diagrams expose the grouped residual block whose widths and groups parameterize that family.
Original paper figure 3–4 — The left diagram defines a network family through stages and blocks; the right diagrams expose the grouped residual block whose widths and groups parameterize that family.

Figure source: [16], Published paper PDF, PDF page 4. Original PDF.

Describe the space before searching it. AnyNet uses a stem, repeated residual stages and a classification head. Stage depth, width, bottleneck ratio and group width define architectural choices. The paper samples models under comparable complexity/training settings and inspects their error distribution. An empirical cumulative distribution function answers what fraction of sampled models achieve error below a chosen threshold; it does not report only the best sample.

Remove freedoms that evidence does not justify. Successive spaces share bottleneck/group choices and favor stage widths that increase with depth. The useful pattern is a simple increasing per-block width sequence, quantized into repeated stage widths. In a simplified account of the parameterization,

uj=w0+waj,qj=round⁡ ⁣(log⁡(uj/w0)/log⁡wm),wj=8round⁡ ⁣(w0wmqj/8).u_j=w_0+w_a j,\quad q_j=\operatorname{round}\!\left(\log(u_j/w_0)/\log w_m\right),\quad w_j=8\operatorname{round}\!\left(w_0w_m^{q_j}/8\right).

j=0,…,d−1j=0,\ldots,d-1 indexes blocks, dd is depth, w0w_0 the initial width, waw_a its linear increment, wm>1w_m>1 a quantization multiplier, and wjw_j the resulting channel count. Equal consecutive widths form stages. Valid group-convolution configurations require additional width/group compatibility checks. The formula alone does not guarantee exactly four stages.

RegNetX uses the residual grouped-convolution block; RegNetY adds squeeze-and-excitation. These are concrete model families generated from the space, not a claim that quantization itself learns the best architecture from images.

Results

The paper compares ImageNet error, complexity and actual GPU inference time across budgets. Its main result is that a compact, structured space can yield competitive models across those budgets. An attractive FLOP count does not by itself establish low latency: the timing comparisons include the effects of width, depth, activation sizes and device execution.

Ablations

The AnyNet-to-RegNet sequence compares sampled distributions as constraints are introduced. A distribution shifting toward lower error is stronger evidence for a useful space than one lucky winning model, but does not mean every sample improves. The per-stage width analyses motivate the quantized linear form; the bottleneck and group studies test which freedoms can be shared or restricted.

Read the sampling and training budget alongside these plots. Restricting the space changes which models can be sampled, so this is a design-space study rather than an isolated layer replacement in one otherwise fixed network.

Conclusion

RegNet’s contribution is a small, interpretable generator of useful network families. It connects architecture design to distributional evidence and separates model complexity from measured hardware speed.

Problems

The design rules were established under particular classification data, blocks and training schedules. They are not universal laws for restoration or other dense tasks. Searching and validating the space still costs compute, and stronger training recipes can alter rankings. A deployment should measure its own resolution, batch size and device rather than inherit a latency claim from a different setup.

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