{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:16:24Z","timestamp":1776888984413,"version":"3.51.2"},"publisher-location":"Cham","reference-count":61,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733369","type":"print"},{"value":"9783031733376","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73337-6_7","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T23:02:27Z","timestamp":1730329347000},"page":"110-128","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["PaPr: Training-Free One-Step Patch Pruning with\u00a0Lightweight ConvNets for\u00a0Faster Inference"],"prefix":"10.1007","author":[{"given":"Tanvir","family":"Mahmud","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Burhaneddin","family":"Yaman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun-Hao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diana","family":"Marculescu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Belharbi, S., Sarraf, A., Pedersoli, M., Ben\u00a0Ayed, I., McCaffrey, L., Granger, E.: F-cam: full resolution class activation maps via guided parametric upscaling. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3490\u20133499 (2022)","DOI":"10.1109\/WACV51458.2022.00378"},{"key":"7_CR2","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your ViT but faster. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Cao, Q., Paranjape, B., Hajishirzi, H.: Pumer: pruning and merging tokens for efficient vision language models. arXiv preprint arXiv:2305.17530 (2023)","DOI":"10.18653\/v1\/2023.acl-long.721"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Chattopadhay, A., Sarkar, A., Howlader, P., Balasubramanian, V.N.: Grad-cam++: generalized gradient-based visual explanations for deep convolutional networks. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 839\u2013847. IEEE (2018)","DOI":"10.1109\/WACV.2018.00097"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, H., Yin, H., Fan, B.: Building vision transformers with hierarchy aware feature aggregation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5908\u20135918 (2023)","DOI":"10.1109\/ICCV51070.2023.00543"},{"key":"7_CR7","unstructured":"Chu, X., et al.: Twins: revisiting the design of spatial attention in vision transformers. In: Advances in Neural Information Processing Systems, vol. 34, pp. 9355\u20139366 (2021)"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., Sun, J.: RepVGG: making VGG-style convnets great again. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13733\u201313742 (2021)","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: Cswin transformer: a general vision transformer backbone with cross-shaped windows. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"7_CR10","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2020)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"7_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1007\/978-3-031-20083-0_24","volume-title":"Computer Vision - ECCV 2022","author":"M Fayyaz","year":"2022","unstructured":"Fayyaz, M., et al.: ATS: adaptive token sampling for efficient vision transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13671, pp. 396\u2013414. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_24"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3d: expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 203\u2013213 (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Graham, B., et al.: Levit: a vision transformer in convnet\u2019s clothing for faster inference. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"7_CR16","unstructured":"Hatamizadeh, A., Yin, H., Heinrich, G., Kautz, J., Molchanov, P.: Global context vision transformers. In: International Conference on Machine Learning, pp. 12633\u201312646. PMLR (2023)"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Howard, A., et\u00a0al.: Searching for mobilenetv3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"7_CR20","unstructured":"Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Jung, H., Oh, Y.: Towards better explanations of class activation mapping. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1336\u20131344 (2021)","DOI":"10.1109\/ICCV48922.2021.00137"},{"key":"7_CR22","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv:1705.06950 [cs.CV] (2017)"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Kim, M., Gao, S., Hsu, Y.C., Shen, Y., Jin, H.: Token fusion: bridging the gap between token pruning and token merging. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1383\u20131392 (2024)","DOI":"10.1109\/WACV57701.2024.00141"},{"key":"7_CR24","unstructured":"Kim, S., et al.: Learned token pruning for transformers. arXiv:2107.00910 [cs.CL] (2021)"},{"key":"7_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1007\/978-3-031-20083-0_37","volume-title":"Computer Vision - ECCV 2022","author":"Z Kong","year":"2022","unstructured":"Kong, Z., et al.: SPViT: enabling faster vision transformers via latency-aware soft token pruning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13671, pp. 620\u2013640. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_37"},{"key":"7_CR26","unstructured":"Lassance, C., Maachou, M., Park, J., Clinchant, S.: A study on token pruning for colBERT. arXiv:2112.06540 [cs.CL] (2021)"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: MViTv2: improved multiscale vision transformers for classification and detection. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"7_CR28","unstructured":"Liang, Y., Ge, C., Tong, Z., Song, Y., Wang, J., Xie, P.: Not all patches are what you need: expediting vision transformers via token reorganizations. ICLR (2022)"},{"key":"7_CR29","unstructured":"Lin, J., Chen, W.M., Cai, H., Gan, C., Han, S.: Memory-efficient patch-based inference for tiny deep learning. In: Advances in Neural Information Processing Systems, vol. 4, pp. 2346\u20132358 (2021)"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., et\u00a0al.: Swin transformer v2: scaling up capacity and resolution. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"7_CR33","unstructured":"Mehta, S., Rastegari, M.: Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. In: ICLR (2021)"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Meng, L., et al.: Adavit: adaptive vision transformers for efficient image recognition. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Muhammad, M.B., Yeasin, M.: Eigen-CAM: class activation map using principal components. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20137. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9206626"},{"key":"7_CR36","unstructured":"Oquab, M., et\u00a0al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"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, pp. 377\u2013386 (2021)","DOI":"10.1109\/ICCV48922.2021.00043"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Patro, B.N., Lunayach, M., Patel, S., Namboodiri, V.P.: U-CAM: visual explanation using uncertainty based class activation maps. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7444\u20137453 (2019)","DOI":"10.1109\/ICCV.2019.00754"},{"key":"7_CR39","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Rao, Y., Liu, Z., Zhao, W., Zhou, J., Lu, J.: Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3263826"},{"key":"7_CR41","unstructured":"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, vol. 34, pp. 13937\u201313949 (2021)"},{"key":"7_CR42","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"7_CR44","doi-asserted-by":"crossref","unstructured":"Singh, M., et al.: Revisiting weakly supervised pre-training of visual perception models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00088"},{"key":"7_CR45","unstructured":"Steiner, A., Kolesnikov, A., Zhai, X., Wightman, R., Uszkoreit, J., Beyer, L.: How to train your vit? Data, augmentation, and regularization in vision transformers. TMLR (2022)"},{"key":"7_CR46","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: ICML (2019)"},{"key":"7_CR47","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. arXiv:2203.12602 [cs.CV] (2022)"},{"key":"7_CR48","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: ICML (2021)"},{"key":"7_CR49","doi-asserted-by":"crossref","unstructured":"Vasu, P.K.A., Gabriel, J., Zhu, J., Tuzel, O., Ranjan, A.: Mobileone: an improved one millisecond mobile backbone. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7907\u20137917 (2023)","DOI":"10.1109\/CVPR52729.2023.00764"},{"key":"7_CR50","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Score-CAM: score-weighted visual explanations for convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 24\u201325 (2020)","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"7_CR51","unstructured":"Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020)"},{"key":"7_CR52","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, C.Y., Yuille, A., Feichtenhofer, C.: Masked feature prediction for self-supervised visual pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14668\u201314678 (2022)","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"7_CR53","doi-asserted-by":"crossref","unstructured":"Woo, S., et al.: Convnext v2: co-designing and scaling convnets with masked autoencoders. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16133\u201316142 (2023)","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"7_CR54","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: CVT: introducing convolutions to vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22\u201331 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"7_CR55","doi-asserted-by":"crossref","unstructured":"Xu, X., Wang, S., Chen, Y., Zheng, Y., Wei, Z., Liu, J.: GTP-VIT: efficient vision transformers via graph-based token propagation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 86\u201395 (2024)","DOI":"10.1109\/WACV57701.2024.00016"},{"key":"7_CR56","doi-asserted-by":"crossref","unstructured":"Yin, H., Vahdat, A., Alvarez, J.M., Mallya, A., Kautz, J., Molchanov, P.: A-VIT: adaptive tokens for efficient vision transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10809\u201310818 (2022)","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"7_CR57","doi-asserted-by":"crossref","unstructured":"You, H., et al.: Castling-VIT: compressing self-attention via switching towards linear-angular attention at vision transformer inference. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14431\u201314442 (2023)","DOI":"10.1109\/CVPR52729.2023.01387"},{"key":"7_CR58","unstructured":"Yu, H., Wu, J.: A unified pruning framework for vision transformers. arXiv:2111.15127 [cs.CV] (2021)"},{"key":"7_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856 (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"7_CR60","doi-asserted-by":"crossref","unstructured":"Zhou, A., et al.: SparseMAE: sparse training meets masked autoencoders. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16176\u201316186 (2023)","DOI":"10.1109\/ICCV51070.2023.01482"},{"key":"7_CR61","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73337-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T23:04:09Z","timestamp":1730329449000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73337-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031733369","9783031733376"],"references-count":61,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73337-6_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}