Lightweight transformer image feature extraction network
Open accessThe DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
In recent years, the image feature extraction method based on Transformer has become a research hotspot. However, when using Transformer for image feature extraction, the model’s complexity increases quadratically with the number of tokens entered. The quadratic complexity prevents vision transformer-based backbone networks from modelling high-resolution images and is computationally expensive. To address this issue, this study proposes two approaches to speed up Transformer models. Firstly, the self-attention mechanism’s quadratic complexity is reduced to linear, enhancing the model’s internal processing speed. Next, a parameter-less lightweight pruning method is introduced, which adaptively samples input images to filter out unimportant tokens, effectively reducing irrelevant input. Finally, these two methods are combined to create an efficient attention mechanism. Experimental results demonstrate that the combined methods can reduce the computation of the original Transformer model by 30%–50%, while the efficient attention mechanism achieves an impressive 60%–70% reduction in computation.
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
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
Wang, X., Girshick, R., Gupta, A., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00813 · Cited by 11,596
A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
Li, Z., Liu, F., Yang, W., Peng, S., & Zhou, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3084827 · Cited by 5,273
Pyramid 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 2×
“In October 2020, Taking PVT ( Wang et al., 2021 ) as an example, it proposes a space reduction module, which first restores the input token sequences of each encoder to the spatial structure, then uses convolution to reduce the dimensions of the spatial structure.”
Han (2023) · doi:10.1109/tpami.2022.3152247 · Cited by 4,682
Transformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022) · ACM Computing Surveys · doi:10.1145/3505244 · Cited by 3,595
Transformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2021) · arXiv · doi:10.48550/arxiv.2101.01169 · Cited by 3,594
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
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. 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×
“In the experiment, six selected benchmark models including DeiT ( Touvron et al., 2021a ), PVT ( Wang et al., 2021 ), Swin Transformer ( Huang et al., 2021 ), TNT ( Han et al., 2021 ), T2T-ViT ( Yuan et al., 2021 ) and CaiT ( Touvron et al., 2021b ).”
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 2×
“The design concept of MViT ( Fan et al., 2021 ) proposed by Facebook in April 2021 is similar to that of PVT, and improved MViT was further proposed in December 2021 ( Li et al., 2022a ).”
Cited by
Hyperspectral imaging and its applications: A review
Bhargava, A., Sachdeva, A., Sharma, K., Alsharif, M. H., Uthansakul, P., & Uthansakul, M. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e33208 · Cited by 277
The major human AP endonuclease (Ape1) is involved in the nucleotide incision repair pathway
Gros, L. (2004) · Nucleic Acids Research · doi:10.1093/nar/gkh165 · Cited by 209
Vehicle recognition pipeline via DeepSort on aerial image datasets
Hanzla, M., Yusuf, M. O., Al Mudawi, N., Sadiq, T., Almujally, N. A., Rahman, H., Alazeb, A., & Algarni, A. (2024) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2024.1430155 · Cited by 18
“Fuzzy logic (Chong et al., 2023; Zheng et al., 2024) refers to pixels that belong to more than one cluster.”
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
- Zheng, W., Lu, S., Yang, Y., Yin, Z., & Yin, L.
- Venue
- PeerJ Computer Science
- Publisher
- PeerJ
- Published
- 2024-01-31
- Volume
- 10
- Pages
- e1755
- ISSN
- 2376-5992 (ISSN-L)
- OpenAlex
- W4391401593
- Cited by
- 162
- References
- 18
- FWCI
- 18.79
- Type
- journal article
- Language
- en
- Open access
- gold
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.