The DOI matches its Crossref record; 55 of the 59 references it cites were found in a registry or an index.
AdaViT: Adaptive Vision Transformers for Efficient Image Recognition
Abstract
Built on top of self-attention mechanisms, vision transformers have demonstrated remarkable performance on a variety of tasks recently. While achieving excellent performance, they still require relatively intensive computational cost that scales up drastically as the numbers of patches, self-attention heads and transformer blocks increase. In this paper, we argue that due to the large variations among images, their need for modeling long-range dependencies between patches differ. To this end, we introduce AdaViT, an adaptive computation framework that learns to derive usage policies on which patches, self-attention heads and transformer blocks to use throughout the backbone on a per-input basis, aiming to improve inference efficiency of vision transformers with a minimal drop of accuracy for image recognition. Optimized jointly with a transformer backbone in an end-to-end manner, a light-weight decision network is attached to the backbone to produce decisions on-the-fly. Extensive experiments on ImageNet demonstrate that our method obtains more than 2 × improvement on efficiency compared to state-of-the-art vision transformers with only 0.8% drop of accuracy, achieving good efficiency/accuracy trade-offs conditioned on different computational budgets. We further conduct quantitative and qualitative analysis on learned usage polices and provide more insights on the redundancy in vision transformers. Code is available at ht tps: / / gi thub. com/MengLcool/AdaVi T.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Yet, token pruning has several disadvantages: the information loss from pruning limits how many tokens you can reasonably reduce;”
From Token Merging: Your ViT But Faster (2022) · cites this paper as Meng et al., 2022
In the citing paper
“current methods require re-training the model to be effective (some with extra parameters);”
From Token Merging: Your ViT But Faster (2022) · cites this paper as Meng et al., 2022
In the citing paper
“and several prune different numbers of tokens depending on the input content, making batched inference infeasible.”
From Token Merging: Your ViT But Faster (2022) · cites this paper as Meng et al., 2022
In the citing paper
“most cannot be applied to speed up training;”
From Token Merging: Your ViT But Faster (2022) · cites this paper as Meng et al., 2022
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
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
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225
MobileNets: 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
Self-citationEnd-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
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
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
Flagged first, then by citations
4 of the 59 references couldn’t be matched to a known paper.
Research works printed but not linked: 5
- pan, 2021, Ia-red2: Interpretability-aware redundancy reduction for vision transformers, NeurIPS
- li, 2021, Localvit: Bringing locality to vision transformers, ArXiv Preprint
- he, 2021, Transreid: Transformer-based object reidentification, ICCV
- dosovitskiy, 2021, An image is worth 16x16 words: Transformers for image recognition at scale, ICLRE
- wang, 2021, Not all images are worth 16x16 words: Dynamic vision transformers with adaptive sequence length, NeurIPS
Cited by
Sorted by citations
ObjectFormer for Image Manipulation Detection and Localization
Wang, J., Wu, Z., Chen, J., Han, X., Shrivastava, A., Lim, S.-N., & Jiang, Y. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00240 · Cited by 275
Self-citationBEVT: BERT Pretraining of Video Transformers
Wang, R., Chen, D., Wu, Z., Chen, Y., Dai, X., Liu, M., Jiang, Y.-G., Zhou, L., & Yuan, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01432 · Cited by 234
Self-citationScale-Aware Modulation Meet Transformer
Lin, W., Wu, Z., Chen, J., Huang, J., & Jin, L. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00553 · Cited by 237
Self-citationA Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends
Younesi, A., Ansari, M., Fazli, M., Ejlali, A., Shafique, M., & Henkel, J. (2024) · IEEE Access · doi:10.1109/access.2024.3376441 · Cited by 241
Prototypical Residual Networks for Anomaly Detection and Localization
Zhang, H., Wu, Z., Wang, Z., Chen, Z., & Jiang, Y. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01562 · Cited by 129
Self-citation
Metadata
- Authors
- Meng, L., Li, H., Chen, B.-C., Lan, S., Wu, Z., Jiang, Y.-G., & Lim, S.-N.
- Affiliations
- Fudan University (CN)
- University of Maryland, College Park (US)
- Meta (United States) (US)
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2022-06
- Pages
- 12299-12308
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4226174225
- Cited by
- 262
- References
- 59
- Citations by year
- 2026: 35 · 2025: 68 · 2024: 106 · 2023: 47 · 2022: 6
- FWCI
- 20.58
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- Funders
- National Key R&D Program of China (2021ZDOI12805)
- 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 › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- vision transformer, adaptive computation, self-attention, inference efficiency, image recognition, influence diagrams, long-range dependencies, accuracy-efficiency trade-off
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
