{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T16:20:39Z","timestamp":1778948439301,"version":"3.51.4"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729485","type":"print"},{"value":"9783031729492","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\/978-3-031-72949-2_21","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:22:17Z","timestamp":1730301737000},"page":"363-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":360,"title":["Wavelet Convolutions for\u00a0Large Receptive Fields"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0254-1380","authenticated-orcid":false,"given":"Shahaf E.","family":"Finder","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4524-0883","authenticated-orcid":false,"given":"Roy","family":"Amoyal","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5351-0966","authenticated-orcid":false,"given":"Eran","family":"Treister","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9816-9709","authenticated-orcid":false,"given":"Oren","family":"Freifeld","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"issue":"18","key":"21_CR1","doi-asserted-by":"publisher","first-page":"7010","DOI":"10.3390\/s22187010","volume":"22","author":"SY Alaba","year":"2022","unstructured":"Alaba, S.Y., Ball, J.E.: WCNN3D: wavelet convolutional neural network-based 3D object detection for autonomous driving. Sensors 22(18), 7010 (2022)","journal-title":"Sensors"},{"issue":"5","key":"21_CR2","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","volume":"43","author":"Z Cai","year":"2019","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: high quality object detection and instance segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1483\u20131498 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Drop an octave: reducing spatial redundancy in convolutional neural networks with octave convolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision,pp. 3435\u20133444 (2019)","DOI":"10.1109\/ICCV.2019.00353"},{"key":"21_CR4","first-page":"4479","volume":"33","author":"L Chi","year":"2020","unstructured":"Chi, L., Jiang, B., Mu, Y.: Fast Fourier convolution. Adv. Neural. Inf. Process. Syst. 33, 4479\u20134488 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"21_CR6","unstructured":"Contributors, M.: MMDetection: OpenMMLab detection toolbox and benchmark (2018). https:\/\/github.com\/open-mmlab\/mmdetection"},{"key":"21_CR7","unstructured":"Contributors, M.: MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark (2020). https:\/\/github.com\/open-mmlab\/mmsegmentation"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Daubechies, I.: Ten Lectures on Wavelets. SIAM (1992)","DOI":"10.1137\/1.9781611970104"},{"key":"21_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":"21_CR10","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Han, J., Ding, G.: Scaling up your kernels to 31$$\\times $$31: revisiting large kernel design in CNNs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11963\u201311975 (2022)","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"21_CR11","unstructured":"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)"},{"key":"21_CR12","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.patcog.2016.11.015","volume":"64","author":"Y Duan","year":"2017","unstructured":"Duan, Y., Liu, F., Jiao, L., Zhao, P., Zhang, L.: SAR image segmentation based on convolutional-wavelet neural network and Markov random field. Pattern Recogn. 64, 255\u2013267 (2017)","journal-title":"Pattern Recogn."},{"key":"21_CR13","unstructured":"Finder, S.E., Zohav, Y., Ashkenazi, M., Treister, E.: Wavelet feature maps compression for image-to-image CNNs. In: Advances in Neural Information Processing Systems (2022)"},{"key":"21_CR14","unstructured":"Fujieda, S., Takayama, K., Hachisuka, T.: Wavelet convolutional neural networks. arXiv preprint arXiv:1805.08620 (2018)"},{"issue":"4","key":"21_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459836","volume":"40","author":"R Gal","year":"2021","unstructured":"Gal, R., Hochberg, D.C., Bermano, A., Cohen-Or, D.: SWAGAN: a style-based wavelet-driven generative model. ACM Trans. Graph. (TOG) 40(4), 1\u201311 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Gavrikov, P., Keuper, J.: Can biases in ImageNet models explain generalization? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22184\u201322194 (2024)","DOI":"10.1109\/CVPR52733.2024.02094"},{"key":"21_CR17","unstructured":"Geirhos, R., et al.: Partial success in closing the gap between human and machine vision. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"21_CR18","unstructured":"Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In: International Conference on Learning Representations (2019)"},{"key":"21_CR19","unstructured":"Grabinski, J., Keuper, J., Keuper, M.: As large as it gets \u2013 studying infinitely large convolutions via neural implicit frequency filters. Trans. Mach. Learn. Res. (2024)"},{"issue":"4","key":"21_CR20","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1007\/s41095-023-0364-2","volume":"9","author":"MH Guo","year":"2023","unstructured":"Guo, M.H., Lu, C.Z., Liu, Z.N., Cheng, M.M., Hu, S.M.: Visual attention network. Comput. Vis. Media 9(4), 733\u2013752 (2023)","journal-title":"Comput. Vis. Media"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Guo, T., Seyed\u00a0Mousavi, H., Huu\u00a0Vu, T., Monga, V.: Deep wavelet prediction for image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 104\u2013113 (2017)","DOI":"10.1109\/CVPRW.2017.148"},{"key":"21_CR22","unstructured":"Guth, F., Coste, S., De\u00a0Bortoli, V., Mallat, S.: Wavelet score-based generative modeling. In: Advances in Neural Information Processing Systems (2022)"},{"key":"21_CR23","unstructured":"Haber, E., Lensink, K., Treister, E., Ruthotto, L.: IMEXnet a forward stable deep neural network. In: Proceedings of the 36th International Conference on Machine Learning (2019)"},{"key":"21_CR24","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":"21_CR25","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: Proceedings of the IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"21_CR26","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: Proceedings of the International Conference on Learning Representations (2019)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"21_CR28","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Huang, H., He, R., Sun, Z., Tan, T.: Wavelet-SRNet: a wavelet-based CNN for multi-scale face super resolution. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1689\u20131697 (2017)","DOI":"10.1109\/ICCV.2017.187"},{"key":"21_CR30","unstructured":"Jeevan, P., Viswanathan, K., Sethi, A., et\u00a0al.: WaveMix: a resource-efficient neural network for image analysis. arXiv preprint arXiv:2205.14375 (2022)"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Robust deep learning object recognition models rely on low frequency information in natural images. PLOS Comput. Biol. (2023)","DOI":"10.1101\/2022.01.31.478509"},{"key":"21_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Liu, P., Zhang, H., Zhang, K., Lin, L., Zuo, W.: Multi-level wavelet-CNN for image restoration. In: Conference on Computer Vision and Pattern Recognition Workshops, pp. 773\u2013782 (2018)","DOI":"10.1109\/CVPRW.2018.00121"},{"key":"21_CR34","unstructured":"Liu, S., et al.: More convnets in the 2020s: Scaling up kernels beyond 51$$\\times $$51 using sparsity. In: International Conference on Learning Representations (2023)"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"21_CR37","unstructured":"Luo, W., Li, Y., Urtasun, R., Zemel, R.: Understanding the effective receptive field in deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"21_CR38","unstructured":"Michaelis, C., et al.: Benchmarking robustness in object detection: autonomous driving when winter is coming. arXiv preprint arXiv:1907.07484 (2019)"},{"key":"21_CR39","unstructured":"Mintun, E., Kirillov, A., Xie, S.: On interaction between augmentations and corruptions in natural corruption robustness. In: Advances in Neural Information Processing Systems (2021)"},{"key":"21_CR40","unstructured":"Naseer, M.M., Ranasinghe, K., Khan, S.H., Hayat, M., Shahbaz Khan, F., Yang, M.H.: Intriguing properties of vision transformers. In: Advances in Neural Information Processing Systems, vol. 34, pp. 23296\u201323308 (2021)"},{"key":"21_CR41","unstructured":"Park, N., Kim, S.: How do vision transformers work? arXiv preprint arXiv:2202.06709 (2022)"},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Phung, H., Dao, Q., Tran, A.: Wavelet diffusion models are fast and scalable image generators. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10199\u201310208 (2023)","DOI":"10.1109\/CVPR52729.2023.00983"},{"key":"21_CR43","unstructured":"Rao, Y., Zhao, W., Zhu, Z., Lu, J., Zhou, J.: Global filter networks for image classification. In: Advances in Neural Information Processing Systems, vol. 34, pp. 980\u2013993 (2021)"},{"key":"21_CR44","doi-asserted-by":"crossref","unstructured":"Ronen, M., Finder, S.E., Freifeld, O.: DeepDPM: deep clustering with an unknown number of clusters. In: Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00963"},{"key":"21_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"21_CR46","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":"21_CR47","doi-asserted-by":"crossref","unstructured":"Saragadam, V., LeJeune, D., Tan, J., Balakrishnan, G., Veeraraghavan, A., Baraniuk, R.G.: WIRE: wavelet implicit neural representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18507\u201318516 (2023)","DOI":"10.1109\/CVPR52729.2023.01775"},{"key":"21_CR48","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"21_CR49","unstructured":"Trockman, A., Kolter, J.Z.: Patches are all you need? Trans. Mach. Learn. Res. (2023)"},{"key":"21_CR50","unstructured":"Tuli, S., Dasgupta, I., Grant, E., Griffiths, T.L.: Are convolutional neural networks or transformers more like human vision? arXiv preprint arXiv:2105.07197 (2021)"},{"key":"21_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1007\/978-3-030-58607-2_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"W Van Gansbeke","year":"2020","unstructured":"Van Gansbeke, W., Vandenhende, S., Georgoulis, S., Proesmans, M., Van Gool, L.: SCAN: learning to classify images without labels. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 268\u2013285. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_16"},{"key":"21_CR52","unstructured":"Vanhoucke, V.: Learning visual representations at scale. In: ICLR Invited Talk, vol. 1, no. 2 (2014)"},{"key":"21_CR53","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"21_CR54","unstructured":"Wang, H., Ge, S., Lipton, Z., Xing, E.P.: Learning robust global representations by penalizing local predictive power. In: Advances in Neural Information Processing Systems, pp. 10506\u201310518 (2019)"},{"key":"21_CR55","doi-asserted-by":"crossref","unstructured":"Wang, H., Wu, X., Huang, Z., Xing, E.P.: High-frequency component helps explain the generalization of convolutional neural networks. In: Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00871"},{"key":"21_CR56","doi-asserted-by":"crossref","unstructured":"Wang, M., Liu, B., Foroosh, H.: Factorized convolutional neural networks. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 545\u2013553 (2017)","DOI":"10.1109\/ICCVW.2017.71"},{"key":"21_CR57","doi-asserted-by":"crossref","unstructured":"Wang, T., Lu, C., Sun, Y., Yang, M., Liu, C., Ou, C.: Automatic ECG classification using continuous wavelet transform and convolutional neural network. Entropy (2021)","DOI":"10.3390\/e23010119"},{"key":"21_CR58","unstructured":"Williams, T., Li, R.: Wavelet pooling for convolutional neural networks. In: International Conference on Learning Representations (2018)"},{"key":"21_CR59","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 418\u2013434 (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"issue":"3","key":"21_CR60","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ADE20K dataset. Int. J. Comput. Vision 127(3), 302\u2013321 (2019)","journal-title":"Int. J. Comput. Vision"}],"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\/978-3-031-72949-2_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:53:27Z","timestamp":1730303607000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72949-2_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031729485","9783031729492"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72949-2_21","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"}}]}}