Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
Open accessThe DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Abstract
Automated design of neural network architectures tailored for a specific task is an extremely promising, albeit inherently difficult, avenue to explore. While most results in this domain have been achieved on image classification and language modelling problems, here we concentrate on dense per-pixel tasks, in particular, semantic image segmentation using fully convolutional networks. In contrast to the aforementioned areas, the design choices of a fully convolutional network require several changes, ranging from the sort of operations that need to be used - e.g., dilated convolutions - to a solving of a more difficult optimisation problem. In this work, we are particularly interested in searching for high-performance compact segmentation architectures, able to run in real-time using limited resources. To achieve that, we intentionally over-parameterise the architecture during the training time via a set of auxiliary cells that provide an intermediate supervisory signal and can be omitted during the evaluation phase. The design of the auxiliary cell is emitted by a controller, a neural network with the fixed structure trained using reinforcement learning. More crucially, we demonstrate how to efficiently search for these architectures within limited time and computational budgets. In particular, we rely on a progressive strategy that terminates non-promising architectures from being further trained, and on Polyak averaging coupled with knowledge distillation to speed-up the convergence. Quantitatively, in 8 GPU-days our approach discovers a set of architectures performing on-par with state-of-the-art among compact models on the semantic segmentation, pose estimation and depth prediction tasks. Code will be made available here: https://github.com/drsleep/nas-segm-pytorch.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · arXiv · doi:10.48550/arxiv.1802.02611 · Cited by 20,063 · cited 2×
“[7] have also shown that the combination of those two paradigms lead to even better results across different benchmarks.”
MethodResultEncoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_49 · Cited by 20,054
Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.660 · Cited by 16,438
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625
Learning Transferable Architectures for Scalable Image Recognition
Zoph, B., Vasudevan, V., Shlens, J., & Le, Q. V. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00907 · Cited by 7,831
Practical Bayesian Optimization of Machine Learning Algorithms
Snoek, J., Larochelle, H., & Adams, R. P. (2012) · arXiv · doi:10.48550/arxiv.1206.2944 · Cited by 6,691
Indoor segmentation and support inference from rgbd images
Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33715-4_54 · Cited by 5,760
Learning Deconvolution Network for Semantic Segmentation
Noh, H., Hong, S., & Han, B. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.178 · Cited by 4,422 · cited 1×
“Two prominent directions have emerged over the last few years: the encoder-decoder type [17, 23, 27], where better features are learned at the expense of having a spatially coarse output mask; whereas other popular approach discards several down-sampling layers and relies on di-”
Background
Research works printed but not linked: 27
- 10.1162/artl.2009.15.2.15202 · DOI · Paper page
- 10.1109/IROS.2018.8594243 · DOI
- 10.1109/CVPR.2013.471 · DOI · Paper page
- sandler, 2018, Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation, Proc IEEE Conf Comp Vis Patt Recogn
- real, 2017, Large-scale evolution of image classifiers, Proc Int Conf Mach Learn
- glorot, 2010, Understanding the difficulty of training deep feedforward neural networks, Proc Conf Artif Intell Statist
- 10.1162/106365602320169811 · DOI · Paper page
- 10.1109/ICCV.2011.6126343 · DOI · Paper page
- hinton, 2014, Distilling the knowledge in a neural network, Proc Advances in Neural Inf Process Syst
- kingma, 2014, Adam: A method for stochastic optimization, ArXiv Computing Research Repository
- lin, 2017, Exploring context with deep structured models for semantic segmentation, IEEE Trans Pattern Anal Mach Intell
- pham, 2018, Efficient neural architecture search via parameter sharing, Proc Int Conf Mach Learn
- bergstra, 2013, Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures, Proc Int Conf Mach Learn
- baker, 2017, Designing neural network architectures using reinforcement learning, Proc Int Conf Learn Representations
- 10.1109/TPAMI.2017.2699184 · DOI · Paper page
- du, 2018, On the power of over-parametrization in neural networks with quadratic activation, Proc Int Conf Mach Learn
- 10.1109/72.265960 · DOI · Paper page
- 10.1007/s11263-009-0275-4 · DOI · Paper page
- 10.1109/CVPR.2014.471 · DOI · Paper page
- lin, 2014, Microsoft COCO: common objects in context, Proc Eur Conf Comp Vis
- liu, 2018, Hierarchical representations for efficient architecture search, Proc Int Conf Learn Representations
- watkins, 1989, Learning from delayed rewards, PhD thesis
- luo, 2018, Neural architecture opti-mization, Proc Advances in Neural Inf Process Syst
- 10.1109/CVPR.2015.7298965 · DOI · Paper page
- 10.1109/CVPR.2017.75 · DOI · Paper page
- nekrasov, 2018, Light-weight refinenet for real-time semantic segmentation, Proc British Machine Vis Conf
- xiao, 2018, Simple baselines for human pose estimation and tracking, Proc Eur Conf Comp Vis
Cited by
Neural Architecture Search: A Survey
Elsken, T., Metzen, J. H., & Hutter, F. (2018) · arXiv · doi:10.48550/arxiv.1808.05377 · Cited by 1,763
AutoML: A survey of the state-of-the-art
He, X., Zhao, K., & Chu, X. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106622 · Cited by 1,691
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M., & Luo, P. (2021) · arXiv · doi:10.48550/arxiv.2105.15203 · Cited by 5,090
Semantic Flow for Fast and Accurate Scene Parsing
Li, X., You, A., Zhu, Z., Zhao, H., Yang, M., Yang, K., Tan, S., & Tong, Y. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_45 · Cited by 416
Rethinking Semantic Segmentation: A Prototype View
Zhou, T., Wang, W., Konukoglu, E., & Van Goo, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00261 · Cited by 376
NAS-FCOS: Fast Neural Architecture Search for Object Detection
Wang, N., Gao, Y., Chen, H., Wang, P., Tian, Z., Shen, C., & Zhang, Y. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01196 · Cited by 258
Self-citationDetNAS: Backbone Search for Object Detection
Chen, Y., Yang, T., Zhang, X., Meng, G., Xiao, X., & Sun, J. (2019) · arXiv · doi:10.48550/arxiv.1903.10979 · Cited by 205
“Some [16] proposes to search auxiliary cells as the segmentation decoders.”
BackgroundRaza, S. M., Abidi, S. M. H., Masuduzzaman, M., & Shin, S. Y. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131357 · Cited by 13
Metadata
- Authors
- Nekrasov, V., Chen, H., Shen, C., & Reid, I.
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 9118-9127
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2898245822
- Cited by
- 157
- References
- 22
- FWCI
- 9.78
- Type
- conference paper
- Language
- en
- Open access
- green
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.