{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T17:34:37Z","timestamp":1783791277123,"version":"3.55.0"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031926471","type":"print"},{"value":"9783031926488","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-92648-8_10","type":"book-chapter","created":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T16:28:32Z","timestamp":1748622512000},"page":"152-169","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Pruning by Explaining Revisited: Optimizing Attribution Methods to\u00a0Prune CNNs and\u00a0Transformers"],"prefix":"10.1007","author":[{"given":"Sayed Mohammad Vakilzadeh","family":"Hatefi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maximilian","family":"Dreyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reduan","family":"Achtibat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Wiegand","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wojciech","family":"Samek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Lapuschkin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"issue":"9","key":"10_CR1","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1038\/s42256-023-00711-8","volume":"5","author":"R Achtibat","year":"2023","unstructured":"Achtibat, R., et al.: From attribution maps to human-understandable explanations through concept relevance propagation. Nat. Mach. Intell. 5(9), 1006\u20131019 (2023)","journal-title":"Nat. Mach. Intell."},{"key":"10_CR2","unstructured":"Achtibat, R., et al.: AttnLRP: attention-aware layer-wise relevance propagation for transformers. In: Proceedings of the 41st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0235, pp. 135\u2013168. PMLR, 21\u201327 July 2024"},{"key":"10_CR3","unstructured":"Ali, A., Schnake, T., Eberle, O., Montavon, G., M\u00fcller, K.R., Wolf, L.: XAI for transformers: Better explanations through conservative propagation. In: International Conference on Machine Learning, pp. 435\u2013451. PMLR (2022)"},{"issue":"7","key":"10_CR4","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140","volume":"10","author":"S Bach","year":"2015","unstructured":"Bach, S., Binder, A., Montavon, G., Klauschen, F., M\u00fcller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7), e0130140 (2015)","journal-title":"PLoS ONE"},{"key":"10_CR5","unstructured":"Balduzzi, D., Frean, M., Leary, L., Lewis, J., Ma, K.W.D., McWilliams, B.: The shattered gradients problem: If resnets are the answer, then what is the question? In: International Conference on Machine Learning, pp. 342\u2013350. PMLR (2017)"},{"key":"10_CR6","doi-asserted-by":"publisher","unstructured":"Becking, D., Dreyer, M., Samek, W., M\u00fcller, K., Lapuschkin, S.: ECQ x: explainability-driven quantization for low-bit and sparse DNNs. In: Holzinger, A., Goebel, R., Fong, R., Moon, T., M\u00fcller, KR., Samek, W. (eds) xxAI - Beyond Explainable AI. xxAI 2020. LNCS, vol. 13200, pp. 271\u2013296. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-031-04083-2_14","DOI":"10.1007\/978-3-031-04083-2_14"},{"key":"10_CR7","unstructured":"Bl\u00fccher, S., Vielhaben, J., Strodthoff, N.: Decoupling pixel flipping and occlusion strategy for consistent XAI benchmarks (2024)"},{"key":"10_CR8","unstructured":"Bommasani, R., et\u00a0al.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"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\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1007\/978-3-319-71589-6_6","volume-title":"Image and Graphics","author":"J Dong","year":"2017","unstructured":"Dong, J., Zheng, H., Lian, L.: Activation-based weight significance criterion for pruning deep neural networks. In: Zhao, Y., Kong, X., Taubman, D. (eds.) ICIG 2017. LNCS, vol. 10667, pp. 62\u201373. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-71589-6_6"},{"key":"10_CR11","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Dreyer, M., Achtibat, R., Wiegand, T., Samek, W., Lapuschkin, S.: Revealing hidden context bias in segmentation and object detection through concept-specific explanations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 3828\u20133838 (2023)","DOI":"10.1109\/CVPRW59228.2023.00397"},{"key":"10_CR13","unstructured":"Fel, T., et al.: A holistic approach to unifying automatic concept extraction and concept importance estimation. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"10_CR14","unstructured":"Frankle, J., Carbin, M.: The lottery ticket hypothesis: finding sparse, trainable neural networks. arXiv preprint arXiv:1803.03635 (2018)"},{"key":"10_CR15","unstructured":"Frazier, P.I.: A tutorial on Bayesian optimization. arXiv preprint arXiv:1807.02811 (2018)"},{"issue":"9","key":"10_CR16","doi-asserted-by":"publisher","first-page":"3161","DOI":"10.1007\/s10994-022-06193-w","volume":"111","author":"L Geng","year":"2022","unstructured":"Geng, L., Niu, B.: Pruning convolutional neural networks via filter similarity analysis. Mach. Learn. 111(9), 3161\u20133180 (2022)","journal-title":"Mach. Learn."},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Gholami, A., Kim, S., Dong, Z., Yao, Z., Mahoney, M.W., Keutzer, K.: A survey of quantization methods for efficient neural network inference. In: Low-Power Computer Vision, pp. 291\u2013326. Chapman and Hall\/CRC (2022)","DOI":"10.1201\/9781003162810-13"},{"key":"10_CR18","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"10_CR19","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":"10_CR20","doi-asserted-by":"crossref","unstructured":"He, Y., Kang, G., Dong, X., Fu, Y., Yang, Y.: Soft filter pruning for accelerating deep convolutional neural networks. In: IJCAI International Joint Conference on Artificial Intelligence (2018)","DOI":"10.24963\/ijcai.2018\/309"},{"issue":"34","key":"10_CR21","first-page":"1","volume":"24","author":"A Hedstr\u00f6m","year":"2023","unstructured":"Hedstr\u00f6m, A., et al.: Quantus: an explainable AI toolkit for responsible evaluation of neural network explanations and beyond. J. Mach. Learn. Res. 24(34), 1\u201311 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR22","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"10_CR23","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456. PMLR (2015)"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Kohlbrenner, M., Bauer, A., Nakajima, S., Binder, A., Samek, W., Lapuschkin, S.: Towards best practice in explaining neural network decisions with LRP. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20137. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9206975"},{"key":"10_CR25","unstructured":"Kuzmin, A., Nagel, M., Van\u00a0Baalen, M., Behboodi, A., Blankevoort, T.: Pruning vs quantization: which is better? In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Lagunas, F., Charlaix, E., Sanh, V., Rush, A.M.: Block pruning for faster transformers. arXiv preprint arXiv:2109.04838 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.829"},{"key":"10_CR27","unstructured":"Lee, J., Park, S., Mo, S., Ahn, S., Shin, J.: Layer-adaptive sparsity for the magnitude-based pruning. In: 9th International Conference on Learning Representations, ICLR 2021 (2021)"},{"key":"10_CR28","first-page":"12934","volume":"35","author":"Y Li","year":"2022","unstructured":"Li, Y., et al.: EfficientFormer: vision transformers at mobilenet speed. Adv. Neural. Inf. Process. Syst. 35, 12934\u201312949 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR29","unstructured":"Lundberg, S.M., Lee, S.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol. 30, pp. 4765\u20134774 (2017)"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Marcel, S., Rodriguez, Y.: Torchvision the machine-vision package of torch. In: Proceedings of the 18th ACM International Conference on Multimedia, pp. 1485\u20131488 (2010)","DOI":"10.1145\/1873951.1874254"},{"key":"10_CR31","unstructured":"Molchanov, P., Tyree, S., Karras, T., Aila, T., Kautz, J.: Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:1611.06440 (2016)"},{"key":"10_CR32","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/978-3-030-28954-6_10","volume-title":"Explainable AI: Interpreting, Explaining and Visualizing Deep Learning","author":"G Montavon","year":"2019","unstructured":"Montavon, G., Binder, A., Lapuschkin, S., Samek, W., M\u00fcller, K.-R.: Layer-wise relevance propagation: an overview. In: Samek, W., Montavon, G., Vedaldi, A., Hansen, L.K., M\u00fcller, K.-R. (eds.) Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. LNCS (LNAI), vol. 11700, pp. 193\u2013209. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-28954-6_10"},{"key":"10_CR33","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/j.patcog.2016.11.008","volume":"65","author":"G Montavon","year":"2017","unstructured":"Montavon, G., Lapuschkin, S., Binder, A., Samek, W., M\u00fcller, K.R.: Explaining nonlinear classification decisions with deep Taylor decomposition. Pattern Recogn. 65, 211\u2013222 (2017)","journal-title":"Pattern Recogn."},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Pahde, F., Yolcu, G.\u00dc., Binder, A., Samek, W., Lapuschkin, S.: Optimizing explanations by network canonization and hyperparameter search. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3818\u20133827 (2023)","DOI":"10.1109\/CVPRW59228.2023.00396"},{"key":"10_CR35","first-page":"8557","volume":"34","author":"A Peste","year":"2021","unstructured":"Peste, A., Iofinova, E., Vladu, A., Alistarh, D.: AC\/DC: alternating compressed\/decompressed training of deep neural networks. Adv. Neural. Inf. Process. Syst. 34, 8557\u20138570 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: \u201cwhy should i trust you?\u201d explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135\u20131144 (2016)","DOI":"10.1145\/2939672.2939778"},{"issue":"11","key":"10_CR37","doi-asserted-by":"publisher","first-page":"2660","DOI":"10.1109\/TNNLS.2016.2599820","volume":"28","author":"W Samek","year":"2017","unstructured":"Samek, W., Binder, A., Montavon, G., Lapuschkin, S., M\u00fcller, K.R.: Evaluating the visualization of what a deep neural network has learned. IEEE Trans. Neural Netw. Learn. Syst. 28(11), 2660\u20132673 (2017)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10_CR38","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: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"10_CR39","unstructured":"Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. In: International Conference on Machine Learning, pp. 3145\u20133153. PMLR (2017)"},{"key":"10_CR40","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations (ICLR 2015). Computational and Biological Learning Society (2015)"},{"key":"10_CR41","unstructured":"Smilkov, D., Thorat, N., Kim, B., Vi\u00e9gas, F., Wattenberg, M.: Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825 (2017)"},{"key":"10_CR42","doi-asserted-by":"crossref","unstructured":"Soroush, K., Raji, M., Ghavami, B.: Compressing deep neural networks using explainable AI. In: 2023 13th International Conference on Computer and Knowledge Engineering (ICCKE), pp. 636\u2013641. IEEE (2023)","DOI":"10.1109\/ICCKE60553.2023.10326237"},{"key":"10_CR43","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: International Conference on Machine Learning, pp. 3319\u20133328. PMLR (2017)"},{"key":"10_CR44","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"10_CR45","doi-asserted-by":"crossref","unstructured":"Voita, E., Talbot, D., Moiseev, F., Sennrich, R., Titov, I.: Analyzing multi-head self-attention: Specialized heads do the heavy lifting, the rest can be pruned. arXiv preprint arXiv:1905.09418 (2019)","DOI":"10.18653\/v1\/P19-1580"},{"key":"10_CR46","unstructured":"Williams, C., Rasmussen, C.: Gaussian processes for regression. In: Advances in Neural Information Processing Systems, vol. 8 (1995)"},{"key":"10_CR47","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.neucom.2022.07.051","volume":"507","author":"C Yang","year":"2022","unstructured":"Yang, C., Liu, H.: Channel pruning based on convolutional neural network sensitivity. Neurocomputing 507, 97\u2013106 (2022)","journal-title":"Neurocomputing"},{"key":"10_CR48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107899","volume":"115","author":"SK Yeom","year":"2021","unstructured":"Yeom, S.K., et al.: Pruning by explaining: a novel criterion for deep neural network pruning. Pattern Recogn. 115, 107899 (2021)","journal-title":"Pattern Recogn."},{"key":"10_CR49","unstructured":"Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., Zou, Y.: DoReFa-Net: training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160 (2016)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-92648-8_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T16:28:49Z","timestamp":1748622529000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-92648-8_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031926471","9783031926488"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-92648-8_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}