The DOI matches its Crossref record; 40 of the 42 references it cites were found in a registry or an index.
Patch Slimming for Efficient Vision Transformers
Open accessAbstract
This paper studies the efficiency problem for visual transformers by excavating redundant calculation in given networks. The recent transformer architecture has demonstrated its effectiveness for achieving excellent performance on a series of computer vision tasks. However, similar to that of convolutional neural networks, the huge computational cost of vision transformers is still a severe issue. Considering that the attention mechanism aggregates different patches layer-by-layer, we present a novel patch slimming approach that discards useless patches in a topdown paradigm. We first identify the effective patches in the last layer and then use them to guide the patch selection process of previous layers. For each layer, the impact of a patch on the final output feature is approximated and patches with less impacts will be removed. Experimental results on benchmark datasets demonstrate that the proposed method can significantly reduce the computational costs of vision transformers without affecting their performances. For example, over 45% FLOPs of the ViT-Ti model can be reduced with only 0.2% top-1 accuracy drop on the ImageNet dataset.
Overview
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
Verification
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Nevertheless, as compared to convolutional neural networks (CNNs), ViTs suffer from higher memory footprints, computational overheads, and power consumption, hindering their deployment and real-time inference on resourceconstrained edge devices [25, 17, 15, 37].”
From I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference (2023) · cites this paper as [37]
Experimental — accuracy not yet measured
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
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
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
(2017) · Cited by 11,625
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 1×
“DeiT-S [38] 4.6 79.8 DeiT-B [38] 17.5 81.8 PVT-Small [40] 3.8 79.8 PVT-Medium [40] 6.7 81.2 PVT-Large [40] 9.8 81.7 T2T-ViT-14 [43] 5.2 81.5 T2T-ViT-19 [43] 8.9 81.9 T2T-ViT-24 [43] 14.1 82.3 TNT-S [12] 5.2 81.5 TNT-B [12] 14.1 82.9 Swin-T [26] 4.5 81.3 Swin-S [26] 8.7 83.0 Swin-B [26] 15.4 83.5…”
InfluentialHan, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Rastegari, M., Ordonez, V., Redmon, J., & Farhadi, A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_32 · Cited by 4,408
Flagged first, then by citations
2 of the 42 references couldn’t be matched to a known paper.
Research works printed but not linked: 6
- touvron, 2020, Training data-efficient image transformers & distillation through at-tention, Arxiv preprint arXiv, 1
- huawei, 2020, Mindspore, 7
- liu, 2018, Frequency-domain dynamic pruning fo convolutional neu-ral networks, Advances in neural information processing systems, 31, 1
- courbariaux, 2016, Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-l, Arxiv preprint arXiv, 1
- dosovitskiy, 2020, An image is worth 16×16 words: Trans-formers for image recognition at scale, Arxiv preprint arXiv, 1
- zhu, 2021, Vi-sual transformer pruning, Arxiv preprint arXiv, 2, 6
Cited by
Sorted by citations
Items 201–202 of 202
Zhang, X., Liu, Y., Pan, X., & Zhang, W. (2026) · Applied Sciences · doi:10.3390/app16199734
IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers
Pan, B., Panda, R., Jiang, Y., Wang, Z., Feris, R., & Oliva, A. (2021) · arXiv · doi:10.48550/arxiv.2106.12620 · Cited by 70
Metadata
- Authors
- Tang, Y., Han, K., Wang, Y., Xu, C., Guo, J., Xu, C., & Tao, D.
- Affiliations
- Peking University (CN)
- Huawei Technologies (China) (CN)
- The University of Sydney (AU)
- Jingdong (China) (CN)
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2022-06
- Pages
- 12155-12164
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4312340826
- Cited by
- 201
- References
- 42
- Citations by year
- 2026: 22 · 2025: 52 · 2024: 49 · 2023: 54 · 2022: 19
- FWCI
- 15.78
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- 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)
- Funders
- National Natural Science Foundation of China (61876007)
- Australian Research Council (DP210101859)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- vision transformer, computational efficiency, attention mechanism, patch selection, FLOPs reduction, ViT
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
