Designing Network Design Spaces
Open accessAbstract
In this work, we present a new network design paradigm. Our goal is to help advance the understanding of network design and discover design principles that generalize across settings. Instead of focusing on designing individual network instances, we design network design spaces that parametrize populations of networks. The overall process is analogous to classic manual design of networks, but elevated to the design space level. Using our methodology we explore the structure aspect of network design and arrive at a low-dimensional design space consisting of simple, regular networks that we call RegNet. The core insight of the RegNet parametrization is surprisingly simple: widths and depths of good networks can be explained by a quantized linear function. We analyze the RegNet design space and arrive at interesting findings that do not match the current practice of network design. The RegNet design space provides simple and fast networks that work well across a wide range of flop regimes. Under comparable training settings and flops, the RegNet models outperform the popular EfficientNet models while being up to 5x faster on GPUs.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The default teacher RegNetY-16GF reaches 82.9% top-1 accuracy on ImageNet.
“This teacher reaches 82 . 9% top-1 accuracy on ImageNet.”
From Training data-efficient image transformers & distillation through attention (2020) · cites this paper as [40]
The RegNetY results in the Additional information section report 19.6% ± 0.16 top-1 error for RegNetY-16GF on ImageNet, equivalent to about 80.4% accuracy, not 82.9%. The paper does not report a result for a separately trained 'default teacher.' (LLM, conf=0.87)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredSwin Transformer achieves a slightly better speed-accuracy trade-off than state-of-the-art ConvNets RegNet and EfficientNet.
“Compared with the state-of-the-art ConvNets, i.e. RegNet [48] and EfficientNet [58], the Swin Transformer achieves a slightly better speed-accuracy trade-off.”
From Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (2021) · cites this paper as [48]
RegNetY shows relatively higher robustness compared to ResNet50, but overall behaves similar to other CNN models.
“RegNetY [50] shows relatively higher robustness when compared to ResNet50, but overall behaves similar to other CNN models.”
From Intriguing Properties of Vision Transformers (2021) · cites this paper as [50]
A similar training with RegNetY-16GF (84M parameters) is 20% slower.
“As a comparison point, a similar training with a RegNetY-16GF [40] (84M parameters) is 20% slower.”
From Training data-efficient image transformers & distillation through attention (2020) · cites this paper as [40]
Compressed GANs can enable GAN-based applications such as style transfer and image synthesis to be efficiently implemented on edge systems.
“By means of compressed GAN, some GAN-based applications, e.g., style transfer, image synthesis, etc, can be efficiently implemented on edge systems.”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [220]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Self-citationBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · see citing works
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · see citing works
Self-citationMobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015 · see citing works
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Tan, M., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1905.11946 · Cited by 17,072 · see citing works
Backpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891 · see citing works
Zagoruyko, S., & Komodakis, N. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.87 · Cited by 7,244 · see citing works
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196 · see citing works
Self-citationImproved regularization of convolutional neural networks with cutout
DeVries, T., & Taylor, G. W. (2017) · arXiv · doi:10.48550/arxiv.1708.04552 · Cited by 2,776 · see citing works
Searching for activation functions
Ramachandran, P., Zoph, B., & Le, Q. V. (2017) · arXiv · doi:10.48550/arxiv.1710.05941 · Cited by 2,335 · see citing works
AutoAugment: Learning Augmentation Policies from Data
Cubuk, E. D., Zoph, B., Mane, D., Vasudevan, V., & Le, Q. V. (2018) · arXiv · doi:10.48550/arxiv.1805.09501 · Cited by 1,106 · see citing works
Do ImageNet Classifiers Generalize to ImageNet?
Recht, B., Roelofs, R., Schmidt, L., & Shankar, V. (2019) · arXiv · doi:10.48550/arxiv.1902.10811 · Cited by 790 · see citing works
On Network Design Spaces for Visual Recognition
Radosavovic, I., Johnson, J., Xie, S., Lo, W.-Y., & Dollar, P. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00197 · Cited by 127 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 22
- F. Chollet. Xception: Deep learning with depthwise separa- ble convolutions. In CVPR, 2017. 7
- J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei- Fei. Imagenet: A large-scale hierarchical image database. In CVPR, 2009. 2, 3, 8, 10
- B. Efron and R. J. Tibshirani. An introduction to the boot- strap. CRC press, 1994. 3
- P. Goyal, P. Dollár, R. Girshick, P. Noordhuis, L. Wesolowski, A. Kyrola, A. Tulloch, Y. Jia, and K. He. Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv:1706.02677, 2017. 11 · arXiv
- J. Hu, L. Shen, and G. Sun. Squeeze-and-excitation net- works. In CVPR, 2018. 7
- G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger. Densely connected convolutional networks. In CVPR, 2017. 2
- A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, 2012. 1, 2
- G. Larsson, M. Maire, and G. Shakhnarovich. Fractalnet: Ultra-deep neural networks without residuals. In ICLR, 2017. 8, 11
- C.-Y. Lee, S. Xie, P. Gallagher, Z. Zhang, and Z. Tu. Deeply- supervised nets. In AISTATS, 2015. 8
- C. Liu, B. Zoph, M. Neumann, J. Shlens, W. Hua, L.-J. Li, L. Fei-Fei, A. Yuille, J. Huang, and K. Murphy. Progressive neural architecture search. In ECCV, 2018. 2, 8
- H. Liu, K. Simonyan, and Y. Yang. Darts: Differentiable architecture search. In ICLR, 2019. 1, 2, 8
- N. Ma, X. Zhang, H.-T. Zheng, and J. Sun. Shufflenet v2: Practical guidelines for efficient cnn architecture design. In ECCV, 2018. 8
- H. Pham, M. Y. Guan, B. Zoph, Q. V. Le, and J. Dean. Ef- ficient neural architecture search via parameter sharing. In ICML, 2018. 2
- E. Real, A. Aggarwal, Y. Huang, and Q. V. Le. Regularized evolution for image classifier architecture search. In AAAI, 2019. 2, 8
- M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen. Mobilenetv2: Inverted residuals and linear bottle- necks. In CVPR, 2018. 2, 7, 8
- K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. In ICLR, 2015. 1, 2
- C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. In CVPR, 2015. 2
- C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna. Rethinking the inception architecture for computer vision. In CVPR, 2016. 2
- S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. He. Aggregated residual transformations for deep neural networks. In CVPR, 2017. 2, 4, 9
- X. Zhang, X. Zhou, M. Lin, and J. Sun. Shufflenet: An extremely efficient convolutional neural network for mobile devices. In CVPR, 2018. 8
- B. Zoph and Q. V. Le. Neural architecture search with rein- forcement learning. In ICLR, 2017. 1
- B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le. Learning transferable architectures for scalable image recognition. In CVPR, 2018. 2, 8
Cited by
Sorted by citations
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534 · see citing works
“RegNet [44], the Swin Transformer achieves a slightly better speed-accuracy trade-off.”
MethodInfluentialYOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00721 · Cited by 13,198 · see citing works
“Model scaling [72, 60, 74, 73, 15, 16, 2, 51] is a way to scale up or down an already designed model and make it fit in different computing devices.”
BackgroundYOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2022) · arXiv · doi:10.48550/arxiv.2207.02696 · Cited by 13,205 · see citing works
“Model scaling [72, 60, 74, 73, 15, 16, 2, 51] is a way to scale up or down an already designed model and make it fit in different computing devices.”
BackgroundLiu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01167 · Cited by 8,494 · see citing works
Emerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00951 · Cited by 5,638 · see citing works
“The second set of models are trained with hard knowledge distillation from a pre-trained supervised RegNetY [56].”
BackgroundMethodInfluentialKnowledge Distillation: A Survey
Gou, J., Yu, B., Maybank, S. J., & Tao, D. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01453-z · Cited by 3,931 · see citing works
RepVGG: Making VGG-style ConvNets Great Again
Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., & Sun, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01352 · Cited by 2,907 · see citing works
Pvt v2: Improved baselines with pyramid vision transformer
Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., & Shao, L. (2022) · Computational Visual Media · doi:10.1007/s41095-022-0274-8 · Cited by 2,439 · see citing works
Scalable Diffusion Models with Transformers
Peebles, W., & Xie, S. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00387 · Cited by 2,284 · see citing works
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking
Zhang, Y., Wang, C., Wang, X., Zeng, W., & Liu, W. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01513-4 · Cited by 1,861 · see citing works
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders
Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., Kweon, I. S., & Xie, S. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01548 · Cited by 1,791 · see citing works
Multiscale vision transformers
Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., & Feichtenhofer, C. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00675 · Cited by 1,407 · see citing works
EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention
Liu, X., Peng, H., Zheng, N., Yang, Y., Hu, H., & Yuan, Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01386 · Cited by 956 · see citing works
Rep ViT: Revisiting Mobile CNN From ViT Perspective
Wang, A., Chen, H., Lin, Z., Han, J., & Ding, G. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01506 · Cited by 752 · see citing works
Conditional Positional Encodings for Vision Transformers
Chu, X., Tian, Z., Zhang, B., Wang, X., & Shen, C. (2021) · arXiv · doi:10.48550/arxiv.2102.10882 · Cited by 489 · see citing works
“Specifically, we use RegNetY-160 (Radosavovic et al., 2020) as the teacher.”
MethodSelf-Supervised Learning in Remote Sensing: A review
Wang, Y., Albrecht, C. M., Braham, N. A. A., Mou, L., & Zhu, X. X. (2022) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2022.3198244 · Cited by 364 · see citing works
AutoFormer: Searching Transformers for Visual Recognition
Chen, M., Peng, H., Fu, J., & Ling, H. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01205 · Cited by 323 · see citing works
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., & Hsieh, C.-J. (2021) · arXiv · doi:10.48550/arxiv.2106.02034 · Cited by 448 · see citing works
Intriguing Properties of Vision Transformers
Naseer, M., Ranasinghe, K., Khan, S., Hayat, M., Khan, F. S., & Yang, M.-H. (2021) · arXiv · doi:10.48550/arxiv.2105.10497 · Cited by 431 · see citing works
Vision Transformers Are Robust Learners
Paul, S., & Chen, P.-Y. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20103 · Cited by 213 · see citing works
Review on self-supervised image recognition using deep neural networks
Ohri, K., & Kumar, M. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107090 · Cited by 179 · see citing works
Training data-efficient image transformers & distillation through attention
Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., & Jégou, H. (2020) · arXiv · doi:10.48550/arxiv.2012.12877 · Cited by 182 · see citing works
SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning
Kong, Z., Dong, P., Ma, X., Meng, X., Niu, W., Sun, M., Shen, X., Yuan, G., Ren, B., Tang, H., et al. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-20083-0_37 · Cited by 169 · see citing works
Bringing ai to edge: from deep learning’s perspective
Liu, D., Kong, H., Luo, X., Liu, W., & Subramaniam, R. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.04.141 · Cited by 171 · see citing works
“We have seen some recent efforts towards defining the effective design space for DNN models [209], [210].”
MethodHRFormer: High-Resolution Transformer for Dense Prediction
Yuan, Y., Fu, R., Huang, L., Lin, W., Zhang, C., Chen, X., & Wang, J. (2021) · arXiv · doi:10.48550/arxiv.2110.09408 · Cited by 178 · see citing works
Neural Architecture Search Survey: A Hardware Perspective
Chitty-Venkata, K. T., & Somani, A. K. (2023) · ACM Computing Surveys · doi:10.1145/3524500 · Cited by 106 · see citing works
Miller, J., Taori, R., Raghunathan, A., Sagawa, S., Koh, P. W., Shankar, V., Liang, P., Carmon, Y., & Schmidt, L. (2021) · arXiv · doi:10.48550/arxiv.2107.04649 · Cited by 74 · see citing works
CondenseNet V2: Sparse Feature Reactivation for Deep Networks
Yang, L., Jiang, H., Cai, R., Wang, Y., Song, S., Huang, G., & Tian, Q. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00357 · Cited by 71 · see citing works
Towards learning-based planning: The nuPlan benchmark for real-world autonomous driving
Karnchanachari, N., Geromichalos, D., Tan, K. S., Li, N., Eriksen, C., Yaghoubi, S., Mehdipour, N., Bernasconi, G., Fong, W. K., Guo, Y., et al. (2024) · 2024 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra57147.2024.10610077 · Cited by 46 · see citing works
“The detector in the first stage takes the point clouds from both the top lidar and side lidars as input and detects the bounding boxes through a large neural network [70].”
MethodEfficient and Lightweight Framework for Real-Time Ore Image Segmentation Based on Deep Learning
Sun, G., Huang, D., Cheng, L., Jia, J., Xiong, C., & Zhang, Y. (2022) · Minerals · doi:10.3390/min12050526 · Cited by 24 · see citing works
Using Sparse Patch Annotation for Tumor Segmentation in Histopathological Images
Liu, Y., He, Q., Duan, H., Shi, H., Han, A., & He, Y. (2022) · Sensors · doi:10.3390/s22166053 · Cited by 10 · see citing works
Zhao, P., Xiao, K., Zhang, Y., Bian, K., & Yan, W. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/290 · Cited by 7 · see citing works
- Authors
- Radosavovic, I., Kosaraju, R. P., Girshick, R., He, K., & Dollar, P.
- Affiliations
- Meta (United States) (US)
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 10425-10433
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3016265891
- Cited by
- 2,084
- References
- 13
- Citations by year
- 2026: 223 · 2025: 424 · 2024: 441 · 2023: 423 · 2022: 311 · 2021: 219 · 2020: 42 · 2019: 1
- FWCI
- 76.73
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- TIB Data Manager
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Keywords
- RegNet
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
