Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Vision Transformers (ViTs) have emerged with superior performance on computer vision tasks compared to the convolutional neural network (CNN)-based models. However, ViTs mainly designed for image classification will generate single-scale low-resolution representations, which makes dense prediction tasks such as semantic segmentation challenging for ViTs. Therefore, we propose HRViT, which enhances ViTs to learn semantically-rich and spatially-precise multi-scale representations by integrating high-resolution multi-branch architectures with ViTs. We balance the model performance and efficiency of HRViT by various branch-block co-optimization techniques. Specifically, we explore heterogeneous branch designs, reduce the redundancy in linear layers, and augment the attention block with enhanced expressiveness. Those approaches enabled HRViT to push the Pareto frontier of performance and efficiency on semantic segmentation to a new level, as our evaluation results on ADE20K and Cityscapes show. HRViT achieves 50.20% mIoU on ADE20K and 83.16% mIoU on Cityscapes, surpassing state-of-the-art MiT and CSWin backbones with an average of +1.78 mIoU improvement, 28% parameter saving, and 21% FLOPs reduction, demonstrating the potential of HRViT as a strong vision backbone for semantic segmentation. Our code is publicly available11https://github.com/facebookresearch/HRViT.
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
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
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
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
Encoder-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
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2644615 · Cited by 19,631
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · arXiv · doi:10.48550/arxiv.2005.12872 · Cited by 18,253
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
The Cityscapes Dataset for Semantic Urban Scene Understanding
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.350 · Cited by 12,433 · cited 2×
“Cityscapes [7] dataset contains 5000 fine-annotated high-resolution images with 19 categories.”
BackgroundMethodStacked Hourglass Networks for Human Pose Estimation
Newell, A., Yang, K., & Deng, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_29 · Cited by 5,634 · cited 1×
“Previous segmentation frameworks progressively down-sample the feature map to compute the LR representations [4, 12, 20], and recover the HR features via up-sampling, e.g., SegNet [1], UNet [24], Hourglass [22].”
MethodPyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., & Shao, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00061 · Cited by 5,259 · cited 6×
“To cope with the challenge, various ViT backbones that yield multi-scale representations were proposed for semantic segmentation [5, 11, 19, 28, 29, 33, 36].”
BackgroundMethodInfluentialDeep High-Resolution Representation Learning for Visual Recognition
Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., et al. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2983686 · Cited by 4,894
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2014) · arXiv · doi:10.48550/arxiv.1412.7062 · Cited by 4,213 · cited 1×
“Convolutional neural networks (CNNs) have rapidly evolved with significant performance improvement in semantic segmentation [1, 4, 18, 20, 24, 27].”
BackgroundRandom Erasing Data Augmentation
Zhong, Z., Zheng, L., Kang, G., Li, S., & Yang, Y. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.7000 · Cited by 3,617
Random Erasing Data Augmentation
Zhong, Z., Zheng, L., Kang, G., Li, S., & Yang, Y. (2017) · arXiv · doi:10.48550/arxiv.1708.04896 · Cited by 3,617 · cited 1×
“We employ label smoothing with a rate of 0.1 and various data augmentation methods used in DeiT [26], including Ran-dAugment [8], Cutmix [39], Mixup [40], and random erasing [42].”
MethodInfluentialRandAugment: Practical automated data augmentation with a reduced search space
Cubuk, E. D., Zoph, B., Shlens, J., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1909.13719 · Cited by 3,223
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z., Tay, F. E., Feng, J., & Yan, S. (2021) · arXiv · doi:10.48550/arxiv.2101.11986 · Cited by 2,415
Self-citationTokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z., Tay, F. E. H., Feng, J., & Yan, S. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00060 · Cited by 2,415 · cited 1×
“Beyond classical CNNs, vision Transformers (ViTs) have emerged with competitive performance in computer vision tasks [2, 3, 5, 11, 12, 17, 19, 26, 29, 30, 33, 34, 37, 41].”
BackgroundSelf-citationUnified Perceptual Parsing for Scene Understanding
Xiao, T., Liu, Y., Zhou, B., Jiang, Y., & Sun, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01228-1_26 · Cited by 2,201
Deep Networks with Stochastic Depth
Huang, G., Sun, Y., Liu, Z., Sedra, D., & Weinberger, K. Q. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_39 · Cited by 2,104
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 · cited 1×
“Several multi-scale ViTs adopt hierarchical architectures to generate progressively down-sampled pyramid features [3, 5, 11, 13, 28, 33].”
BackgroundLeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference
Graham, B., El-Nouby, A., Touvron, H., Stock, P., Joulin, A., Jegou, H., & Douze, M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01204 · Cited by 935 · cited 1×
“We do not use attention operations in the stem since early convolutions are more effective to extract low-level features than self-attentions [14,32].”
MethodTwins: Revisiting the Design of Spatial Attention in Vision Transformers
Chu, X., Tian, Z., Wang, Y., Zhang, B., Ren, H., Wei, X., Xia, H., & Shen, C. (2021) · arXiv · doi:10.48550/arxiv.2104.13840 · Cited by 817
Lite-HRNet: A Lightweight High-Resolution Network
Yu, C., Xiao, B., Gao, C., Yuan, L., Zhang, L., Sang, N., & Wang, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01030 · Cited by 557
HRFormer: 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 · cited 1×
“HRFormer [38] improves HRNetV2 by replacing residual blocks with Swin Trans-former blocks.”
Method
Cited by
HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation
Heidari, M., Kazerouni, A., Soltany, M., Azad, R., Aghdam, E. K., Cohen-Adad, J., & Merhof, D. (2023) · 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv56688.2023.00614 · Cited by 530
Advances in medical image analysis with vision Transformers: A comprehensive review
Azad, R., Kazerouni, A., Heidari, M., Aghdam, E. K., Molaei, A., Jia, Y., Jose, A., Roy, R., & Merhof, D. (2024) · Medical Image Analysis · doi:10.1016/j.media.2023.103000 · Cited by 485
TransUNetCD: A Hybrid Transformer Network for Change Detection in Optical Remote-Sensing Images
Li, Q., Zhong, R., Du, X., & Du, Y. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3169479 · Cited by 347
Metadata
- Authors
- Gu, J., Kwon, H., Wang, D., Ye, W., Li, M., Chen, Y.-H., Lai, L., Chandra, V., & Pan, D. Z.
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2022-06
- Pages
- 12084-12093
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4312726009
- Cited by
- 251
- References
- 26
- FWCI
- 22.12
- 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.