Skip to main content

SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Abstract

Recently, Vision Transformer (ViT) has continuously established new milestones in the computer vision field, while the high computation and memory cost makes its propagation in industrial production difficult. Considering the computation complexity, the internal data pattern of ViTs, and the edge device deployment, we propose a latency-aware soft token pruning framework, SPViT, which can be set up on vanilla Transformers of both flatten and hierarchical structures, such as DeiTs and Swin-Transformers (Swin). More concretely, we design a dynamic attention-based multi-head token selector, which is a lightweight module for adaptive instance-wise token selection. We further introduce a soft pruning technique, which integrates the less informative tokens chosen by the selector module into a package token rather than discarding them completely. SPViT is bound to the trade-off between accuracy and latency requirements of specific edge devices through our proposed latency-aware training strategy. Experiment results show that SPViT significantly reduces the computation cost of ViTs with comparable performance on image classification. Moreover, SPViT can guarantee the identified model meets the latency specifications of mobile devices and FPGA, and even achieve the real-time execution of DeiT-T on mobile devices. For example, SPViT reduces the latency of DeiT-T to 26 ms (26%−41% superior to existing works) on the mobile device with 0.25%−4% higher top-1 accuracy on ImageNet. Our code is released at https://github.com/PeiyanFlying/SPViT.

Z. Kong and P. Dong—Both authors contributed equally.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    Real-time inference usually means 30 frames per second, which is approximately 33 ms/image.

References

  1. Amini, A., Periyasamy, A.S., Behnke, S.: T6d-direct: transformers for multi-object 6d pose direct regression. arXiv preprint arXiv:2109.10948 (2021)

  2. Bao, H., Dong, L., Piao, S., Wei, F.: BEit: BERT pre-training of image transformers. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=p-BhZSz59o4

  3. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213–229. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_13

    Chapter  Google Scholar 

  4. Chang, S.E., et al.: Mix and match: a novel fpga-centric deep neural network quantization framework. In: 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 208–220. IEEE (2021)

    Google Scholar 

  5. Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 782–791 (2021)

    Google Scholar 

  6. Chen, B., et al.: Psvit: better vision transformer via token pooling and attention sharing. arXiv preprint arXiv:2108.03428 (2021)

  7. Chen, C.F.R., Fan, Q., Panda, R.: Crossvit: cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 357–366 (2021)

    Google Scholar 

  8. Chen, H., et al.: Pre-trained image processing transformer. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12299–12310 (2021)

    Google Scholar 

  9. Chen, M., Peng, H., Fu, J., Ling, H.: Autoformer: searching transformers for visual recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 12270–12280 (2021)

    Google Scholar 

  10. Chen, P., Chen, Y., Liu, S., Yang, M., Jia, J.: Exploring and improving mobile level vision transformers. arXiv preprint arXiv:2108.13015 (2021)

  11. Chen, T., Chen, X., Ma, X., Wang, Y., Wang, Z.: Coarsening the granularity: towards structurally sparse lottery tickets. In: Proceedings of the International Conference on Machine Learning (ICML) (2022)

    Google Scholar 

  12. Chen, T., Cheng, Y., Gan, Z., Yuan, L., Zhang, L., Wang, Z.: Chasing sparsity in vision transformers: an end-to-end exploration. In: Advances in Neural Information Processing Systems (2021)

    Google Scholar 

  13. Chen, T., Saxena, S., Li, L., Fleet, D.J., Hinton, G.: Pix2seq: a language modeling framework for object detection. arXiv preprint arXiv:2109.10852 (2021)

  14. Chen, X., Hsieh, C.J., Gong, B.: When vision transformers outperform resnets without pre-training or strong data augmentations. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=LtKcMgGOeLt

  15. Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H.: Transformer tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8126–8135 (2021)

    Google Scholar 

  16. Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021). https://openreview.net/forum?id=0lz69oI5iZP

  17. Chu, C., et al.: Pim-prune: fine-grain dcnn pruning for crossbar-based process-in-memory architecture. In: 2020 57th ACM/IEEE Design Automation Conference (DAC), pp. 1–6. IEEE (2020)

    Google Scholar 

  18. Chu, X., et al.: Conditional positional encodings for vision transformers. arXiv preprint arXiv:2102.10882 (2021)

  19. Dai, Z., Cai, B., Lin, Y., Chen, J.: Up-detr: unsupervised pre-training for object detection with transformers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1601–1610 (2021)

    Google Scholar 

  20. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009). https://doi.org/10.1109/CVPR.2009.5206848

  21. Deng, J., Yang, Z., Chen, T., Zhou, W., Li, H.: Transvg: end-to-end visual grounding with transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1769–1779 (2021)

    Google Scholar 

  22. Dosovitskiy, A., et al.: An image is worth 16 \(\times \) 16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021). https://openreview.net/forum?id=YicbFdNTTy

  23. El-Nouby, A., Neverova, N., Laptev, I., Jégou, H.: Training vision transformers for image retrieval. arXiv preprint arXiv:2102.05644 (2021)

  24. El-Nouby, A., et al.: XCit: Cross-covariance image transformers. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021). https://openreview.net/forum?id=kzPtpIpF8o

  25. Fang, H., Mei, Z., Shrestha, A., Zhao, Z., Li, Y., Qiu, Q.: Encoding, model, and architecture: systematic optimization for spiking neural network in fpgas. In: 2020 IEEE/ACM International Conference On Computer Aided Design (ICCAD), pp. 1–9. IEEE (2020)

    Google Scholar 

  26. Fang, H., Shrestha, A., Zhao, Z., Qiu, Q.: Exploiting neuron and synapse filter dynamics in spatial temporal learning of deep spiking neural network. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence. IJCAI 2020 (2021)

    Google Scholar 

  27. Fang, H., Taylor, B., Li, Z., Mei, Z., Li, H.H., Qiu, Q.: Neuromorphic algorithm-hardware codesign for temporal pattern learning. In: 2021 58th ACM/IEEE Design Automation Conference (DAC), pp. 361–366. IEEE (2021)

    Google Scholar 

  28. Fayyaz, M., et al.: Ats: adaptive token sampling for efficient vision transformers. arXiv preprint arXiv:2111.15667 (2021)

  29. Gao, P., Lu, J., Li, H., Mottaghi, R., Kembhavi, A.: Container: context aggregation network. arXiv preprint arXiv:2106.01401 (2021)

  30. Gong, Y., et al.: A privacy-preserving-oriented dnn pruning and mobile acceleration framework. In: Proceedings of the 2020 on Great Lakes Symposium on VLSI, pp. 119–124 (2020)

    Google Scholar 

  31. Graham, B., et al.: Levit: a vision transformer in convnet’s clothing for faster inference. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 12259–12269 (2021)

    Google Scholar 

  32. Guo, C., et al.: Accelerating sparse dnn models without hardware-support via tile-wise sparsity. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1–15. IEEE (2020)

    Google Scholar 

  33. Guo, M.H., Cai, J.X., Liu, Z.N., Mu, T.J., Martin, R.R., Hu, S.M.: Pct: point cloud transformer. Comput. Visual Media 7(2), 187–199 (2021)

    Article  Google Scholar 

  34. Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., Wang, Y.: Transformer in transformer. In: Advances in Neural Information Processing Systems (2021)

    Google Scholar 

  35. Heo, B., Yun, S., Han, D., Chun, S., Choe, J., Oh, S.J.: Rethinking spatial dimensions of vision transformers. In: International Conference on Computer Vision (ICCV) (2021)

    Google Scholar 

  36. Hou, Z., et al.: Chex: channel exploration for cnn model compression. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12287–12298 (2022)

    Google Scholar 

  37. Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)

    Google Scholar 

  38. Hudson, D.A., Zitnick, C.L.: Generative adversarial transformers. In: Proceedings of the 38th International Conference on Machine Learning, ICML 2021 (2021)

    Google Scholar 

  39. Jia, D., et al.: Efficient vision transformers via fine-grained manifold distillation. arXiv preprint arXiv:2107.01378 (2021)

  40. Jiang, Z., et al.: All tokens matter: token labeling for training better vision transformers. arXiv preprint arXiv:2104.10858 (2021)

  41. Kim, B., Lee, J., Kang, J., Kim, E.S., Kim, H.J.: Hotr: end-to-end human-object interaction detection with transformers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 74–83 (2021)

    Google Scholar 

  42. Kornblith, S., Norouzi, M., Lee, H., Hinton, G.: Similarity of neural network representations revisited. In: International Conference on Machine Learning, pp. 3519–3529. PMLR (2019)

    Google Scholar 

  43. Li, B., et al.: Efficient transformer-based large scale language representations using hardware-friendly block structured pruning. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 3187–3199 (2020)

    Google Scholar 

  44. Li, Y., Fang, H., Li, M., Ma, Y., Qiu, Q.: Neural network pruning and fast training for drl-based uav trajectory planning. In: 2022 27th Asia and South Pacific Design Automation Conference (ASP-DAC), pp. 574–579. IEEE (2022)

    Google Scholar 

  45. Li, Z., et al.: Revisiting stereo depth estimation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6197–6206 (2021)

    Google Scholar 

  46. Liang, Y., GE, C., Tong, Z., Song, Y., Wang, J., Xie, P.: EVit: expediting vision transformers via token reorganizations. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=BjyvwnXXVn_

  47. Liu, N., et al.: Lottery ticket preserves weight correlation: is it desirable or not? In: International Conference on Machine Learning (ICML), pp. 7011–7020. PMLR (2021)

    Google Scholar 

  48. Liu, Y., Sangineto, E., Bi, W., Sebe, N., Lepri, B., De Nadai, M.: Efficient training of visual transformers with small-size datasets. arXiv preprint arXiv:2106.03746 (2021)

  49. Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision (ICCV) (2021)

    Google Scholar 

  50. Lu, Z., Liu, H., Li, J., Zhang, L.: Efficient transformer for single image super-resolution. arXiv preprint arXiv:2108.11084 (2021)

  51. Ma, X., et al.: PCONV: the missing but desirable sparsity in DNN weight pruning for real-time execution on mobile devices. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol. 34, pp. 5117–5124 (2020)

    Google Scholar 

  52. Ma, X., et al.: Non-structured dnn weight pruning-is it beneficial in any platform? In: IEEE Transactions on Neural Networks and Learning Systems (TNNLS) (2021)

    Google Scholar 

  53. Ma, X., et al.: An image enhancing pattern-based sparsity for real-time inference on mobile devices. In: Proceedings of the European conference on computer vision (ECCV). pp. 629–645. Springer (2020). https://doi.org/10.1007/978-3-030-58601-0_37

  54. Ma, X., et al.: Effective model sparsification by scheduled grow-and-prune methods. In: Proceedings of the International Conference on Learning Representations (ICLR) (2021)

    Google Scholar 

  55. Ma, X., et al.: Blcr: Towards real-time dnn execution with block-based reweighted pruning. In: International Symposium on Quality Electronic Design (ISQED), pp. 1–8. IEEE (2022)

    Google Scholar 

  56. Ma, X., et al.: Tiny but accurate: a pruned, quantized and optimized memristor crossbar framework for ultra efficient dnn implementation. In: 2020 25th Asia and South Pacific design automation conference (ASP-DAC), pp. 301–306. IEEE (2020)

    Google Scholar 

  57. Ma, X., et al.: Sanity checks for lottery tickets: Does your winning ticket really win the jackpot? In: Advances in Neural Information Processing Systems (NeurIPS) 34 (2021)

    Google Scholar 

  58. Mao, M., et al.: Dual-stream network for visual recognition. In: Advances in Neural Information Processing Systems (2021)

    Google Scholar 

  59. Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: Trackformer: multi-object tracking with transformers. arXiv preprint arXiv:2101.02702 (2021)

  60. Misra, I., Girdhar, R., Joulin, A.: An end-to-end transformer model for 3d object detection. In: ICCV (2021)

    Google Scholar 

  61. Niu, W., et al.: A compression-compilation framework for on-mobile real-time bert applications. arXiv preprint arXiv:2106.00526 (2021)

  62. Niu, W., et al.: Grim: A general, real-time deep learning inference framework for mobile devices based on fine-grained structured weight sparsity. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2021)

    Google Scholar 

  63. Niu, W., et al.: Patdnn: achieving real-time dnn execution on mobile devices with pattern-based weight pruning. In: Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), pp. 907–922 (2020)

    Google Scholar 

  64. Pan, B., Jiang, Y., Panda, R., Wang, Z., Feris, R., Oliva, A.: Ia-red\(^2\): Interpretability-aware redundancy reduction for vision transformers. In: Advances in Neural Information Processing Systems (2021)

    Google Scholar 

  65. Pan, Z., Zhuang, B., Liu, J., He, H., Cai, J.: Scalable vision transformers with hierarchical pooling. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 377–386 (2021)

    Google Scholar 

  66. Prillo, S., Eisenschlos, J.: Softsort: a continuous relaxation for the argsort operator. In: International Conference on Machine Learning, pp. 7793–7802. PMLR (2020)

    Google Scholar 

  67. Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Dollár, P.: Designing network design spaces. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10428–10436 (2020)

    Google Scholar 

  68. Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., Dosovitskiy, A.: Do vision transformers see like convolutional neural networks? arXiv preprint arXiv:2108.08810 (2021)

  69. Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: Dynamicvit: efficient vision transformers with dynamic token sparsification. In: Advances in Neural Information Processing Systems (2021)

    Google Scholar 

  70. Ren, A., et al.: Admm-nn: an algorithm-hardware co-design framework of dnns using alternating direction methods of multipliers. In: Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 925–938 (2019)

    Google Scholar 

  71. Renggli, C., Pinto, A.S., Houlsby, N., Mustafa, B., Puigcerver, J., Riquelme, C.: Learning to merge tokens in vision transformers. arXiv preprint arXiv:2202.12015 (2022)

  72. Rumi, M.A., Ma, X., Wang, Y., Jiang, P.: Accelerating sparse cnn inference on gpus with performance-aware weight pruning. In: Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques (PACT), pp. 267–278 (2020)

    Google Scholar 

  73. Ryoo, M.S., Piergiovanni, A., Arnab, A., Dehghani, M., Angelova, A.: Tokenlearner: what can 8 learned tokens do for images and videos? In: Advances in Neural Information Processing Systems (2021)

    Google Scholar 

  74. Sanh, V., Wolf, T., Rush, A.M.: Movement pruning: adaptive sparsity by fine-tuning. arXiv preprint arXiv:2005.07683 (2020)

  75. Srinivas, A., Lin, T.Y., Parmar, N., Shlens, J., Abbeel, P., Vaswani, A.: Bottleneck transformers for visual recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16519–16529 (2021)

    Google Scholar 

  76. Steiner, A., Kolesnikov, A., Zhai, X., Wightman, R., Uszkoreit, J., Beyer, L.: How to train your vit? data, augmentation, and regularization in vision transformers. arXiv preprint arXiv:2106.10270 (2021)

  77. Tan, Z., et al.: Pcnn: pattern-based fine-grained regular pruning towards optimizing cnn accelerators. In: 2020 57th ACM/IEEE Design Automation Conference (DAC), pp. 1–6. IEEE (2020)

    Google Scholar 

  78. Tang, Y., et al.: Patch slimming for efficient vision transformers (2021)

    Google Scholar 

  79. Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J’egou, H.: Training data-efficient image transformers & distillation through attention. In: ICML (2021)

    Google Scholar 

  80. Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)

    Google Scholar 

  81. Wang, H., Zhang, Z., Han, S.: Spatten: efficient sparse attention architecture with cascade token and head pruning. In: 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 97–110. IEEE (2021)

    Google Scholar 

  82. Wang, P., et al.: Kvt: k-nn attention for boosting vision transformers. arXiv preprint arXiv:2106.00515 (2021)

  83. Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: IEEE ICCV (2021)

    Google Scholar 

  84. Wu, B., et al.: Visual transformers: token-based image representation and processing for computer vision. arXiv preprint arXiv:2006.03677 (2020)

  85. Wu, H., et al.: Cvt: introducing convolutions to vision transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 22–31 (2021)

    Google Scholar 

  86. Wu, K., Peng, H., Chen, M., Fu, J., Chao, H.: Rethinking and improving relative position encoding for vision transformer. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10033–10041 (2021)

    Google Scholar 

  87. Xu, C., et al.: You only group once: efficient point-cloud processing with token representation and relation inference module. arXiv preprint arXiv:2103.09975 (2021)

  88. Xu, W., Xu, Y., Chang, T., Tu, Z.: Co-scale conv-attentional image transformers. arXiv preprint arXiv:2104.06399 (2021)

  89. Xu, Y., et al.: Evo-vit: slow-fast token evolution for dynamic vision transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence (2022)

    Google Scholar 

  90. Xue, F., Wang, Q., Guo, G.: Transfer: learning relation-aware facial expression representations with transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3601–3610 (2021)

    Google Scholar 

  91. Yan, B., Peng, H., Fu, J., Wang, D., Lu, H.: Learning spatio-temporal transformer for visual tracking. arXiv preprint arXiv:2103.17154 (2021)

  92. Yang, C., Wu, Z., Zhou, B., Lin, S.: Instance localization for self-supervised detection pretraining. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3987–3996 (2021)

    Google Scholar 

  93. Yang, F., Yang, H., Fu, J., Lu, H., Guo, B.: Learning texture transformer network for image super-resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5791–5800 (2020)

    Google Scholar 

  94. Yang, G., Tang, H., Ding, M., Sebe, N., Ricci, E.: Transformer-based attention networks for continuous pixel-wise prediction. In: ICCV (2021)

    Google Scholar 

  95. Yu, H., Wu, J.: A unified pruning framework for vision transformers. arXiv preprint arXiv:2111.15127 (2021)

  96. Yu, Q., Xia, Y., Bai, Y., Lu, Y., Yuille, A., Shen, W.: Glance-and-gaze vision transformer. In: Advances in Neural Information Processing Systems (2021)

    Google Scholar 

  97. Yu, S., et al.: Unified visual transformer compression. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=9jsZiUgkCZP

  98. Yuan, G., et al.: Tinyadc: Peripheral circuit-aware weight pruning framework for mixed-signal dnn accelerators. In: 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp. 926–931. IEEE (2021)

    Google Scholar 

  99. Yuan, G., et al.: Improving dnn fault tolerance using weight pruning and differential crossbar mapping for reram-based edge ai. In: 2021 22nd International Symposium on Quality Electronic Design (ISQED), pp. 135–141. IEEE (2021)

    Google Scholar 

  100. Yuan, G., et al.: An ultra-efficient memristor-based dnn framework with structured weight pruning and quantization using admm. In: 2019 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED), pp. 1–6. IEEE (2019)

    Google Scholar 

  101. Yuan, G., et al.: Mest: accurate and fast memory-economic sparse training framework on the edge. In: Advances in Neural Information Processing Systems (NeurIPS) 34 (2021)

    Google Scholar 

  102. Yuan, K., Guo, S., Liu, Z., Zhou, A., Yu, F., Wu, W.: Incorporating convolution designs into visual transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 579–588 (2021)

    Google Scholar 

  103. Yuan, L., et al.: Tokens-to-token vit: training vision transformers from scratch on imagenet. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 558–567 (2021)

    Google Scholar 

  104. Yuan, L., et al.: Tokens-to-token vit: training vision transformers from scratch on imagenet. arXiv preprint arXiv:2101.11986 (2021)

  105. Yue, X., Sun, S., Kuang, Z., Wei, M., Torr, P.H., Zhang, W., Lin, D.: Vision transformer with progressive sampling. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 387–396 (2021)

    Google Scholar 

  106. Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. arXiv preprint arXiv:2106.04560 (2021)

  107. Zhang, T., et al.: A unified dnn weight pruning framework using reweighted optimization methods. In: 2021 58th ACM/IEEE Design Automation Conference (DAC), pp. 493–498. IEEE (2021)

    Google Scholar 

  108. Zhang, T., et al.: Structadmm: achieving ultrahigh efficiency in structured pruning for dnns. In: IEEE Transactions on Neural Networks and Learning Systems (TNNLS) (2021)

    Google Scholar 

  109. Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 16259–16268 (2021)

    Google Scholar 

  110. Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881–6890 (2021)

    Google Scholar 

  111. Zhou, D., et al.: Refiner: refining self-attention for vision transformers (2021)

    Google Scholar 

  112. Zhu, M., Han, K., Tang, Y., Wang, Y.: Visual transformer pruning. In: KDD 2021 Workshop on Model Mining (2021)

    Google Scholar 

Download references

Acknowledgments

The research reported here was funded in whole or in part by the Army Research Office/Army Research Laboratory via grant W911-NF-20-1-0167 to Northeastern University. Any errors and opinions are not those of the Army Research Office or Department of Defense and are attributable solely to the author(s). This research is also partially supported by National Science Foundation CCF-1919117 and CMMI-2125326.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Yanzhi Wang .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 17268 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Kong, Z. et al. (2022). SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13671. Springer, Cham. https://doi.org/10.1007/978-3-031-20083-0_37

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20083-0_37

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20082-3

  • Online ISBN: 978-3-031-20083-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics