{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:14:02Z","timestamp":1778084042653,"version":"3.51.4"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730238","type":"print"},{"value":"9783031730245","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"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\/978-3-031-73024-5_4","type":"book-chapter","created":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T16:39:55Z","timestamp":1732552795000},"page":"51-68","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Modality Translation for\u00a0Object Detection Adaptation Without Forgetting Prior Knowledge"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1300-3337","authenticated-orcid":false,"given":"Heitor Rapela","family":"Medeiros","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2289-3690","authenticated-orcid":false,"given":"Masih","family":"Aminbeidokhti","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9999-5321","authenticated-orcid":false,"given":"Fidel Alejandro Guerrero","family":"Pe\u00f1a","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6617-6246","authenticated-orcid":false,"given":"David","family":"Latortue","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6116-7945","authenticated-orcid":false,"given":"Eric","family":"Granger","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7601-8640","authenticated-orcid":false,"given":"Marco","family":"Pedersoli","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,24]]},"reference":[{"key":"4_CR1","unstructured":"Biewald, L.: Experiment tracking with weights and biases (2020). wandb.com"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Bustos, N., Mashhadi, M., Lai-Yuen, S.K., Sarkar, S., Das, T.K.: A systematic literature review on object detection using near infrared and thermal images. Neurocomputing 126804 (2023)","DOI":"10.1016\/j.neucom.2023.126804"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Cao, Y., Bin, J., Hamari, J., Blasch, E., Liu, Z.: Multimodal object detection by channel switching and spatial attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 403\u2013411 (2023)","DOI":"10.1109\/CVPRW59228.2023.00046"},{"key":"4_CR4","doi-asserted-by":"publisher","unstructured":"Chelba, C., Acero, A.: Adaptation of maximum entropy capitalizer: little data can help a lot. Comput. Speech Lang. 20(4), 382\u2013399 (2006). https:\/\/doi.org\/10.1016\/j.csl.2005.05.005, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0885230805000276","DOI":"10.1016\/j.csl.2005.05.005"},{"key":"4_CR5","unstructured":"Chen, J., Li, K., Deng, Q., Li, K., Philip, S.Y.: Distributed deep learning model for intelligent video surveillance systems with edge computing. IEEE Trans. Ind. Inform. (2019)"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Chen, S., Hou, Y., Cui, Y., Che, W., Liu, T., Yu, X.: Recall and learn: fine-tuning deep pretrained language models with less forgetting. CoRR abs\/2004.12651 (2020). https:\/\/arxiv.org\/abs\/2004.12651","DOI":"10.18653\/v1\/2020.emnlp-main.634"},{"issue":"70","key":"4_CR7","doi-asserted-by":"publisher","first-page":"4101","DOI":"10.21105\/joss.04101","volume":"7","author":"NS Detlefsen","year":"2022","unstructured":"Detlefsen, N.S., et al.: Torchmetrics-measuring reproducibility in pytorch. J. Open Sour. Softw. 7(70), 4101 (2022)","journal-title":"J. Open Sour. Softw."},{"key":"4_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1007\/978-3-031-25072-9_46","volume-title":"Computer Vision \u2013 ECCV 2022 Workshops","author":"T Dubail","year":"2022","unstructured":"Dubail, T., Guerrero Pe\u00f1a, F.A., Medeiros, H.R., Aminbeidokhti, M., Granger, E., Pedersoli, M.: Privacy-preserving person detection using low-resolution infrared cameras. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) ECCV 2022. LNCS, vol. 13805, pp. 689\u2013702. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-25072-9_46"},{"key":"4_CR9","doi-asserted-by":"publisher","unstructured":"Falcon, W.: The PyTorch lightning team: PyTorch lightning (2019). https:\/\/doi.org\/10.5281\/zenodo.3828935","DOI":"10.5281\/zenodo.3828935"},{"key":"4_CR10","unstructured":"Feng, H., et al.: CoSDA: continual source-free domain adaptation (2023)"},{"key":"4_CR11","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Processing Syst. 27 (2014)"},{"key":"4_CR12","unstructured":"Group, F., et\u00a0al.: FLIR thermal dataset for algorithm training (2018)"},{"key":"4_CR13","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":"4_CR14","unstructured":"Herrmann, C., Ruf, M., Beyerer, J.: CNN-based thermal infrared person detection by domain adaptation. In: Autonomous Systems: Sensors, Vehicles, Security, and the Internet of Everything, vol. 10643, p. 1064308. International Society for Optics and Photonics (2018)"},{"key":"4_CR15","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"4_CR16","unstructured":"Howard, J., Ruder, S.: Fine-tuned language models for text classification. CoRR abs\/1801.06146 (2018). http:\/\/arxiv.org\/abs\/1801.06146"},{"key":"4_CR17","unstructured":"Hsu, H.K., et al.: Progressive domain adaptation for object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 749\u2013757 (2020)"},{"key":"4_CR18","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"4_CR20","unstructured":"Iakubovskii, P.: Segmentation models pytorch (2019)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Jia, X., Zhu, C., Li, M., Tang, W., Zhou, W.: LLVIP: a visible-infrared paired dataset for low-light vision. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3496\u20133504 (2021)","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Jing, C., Potgieter, J., Noble, F., Wang, R.: A comparison and analysis of RGB-D cameras\u2019 depth performance for robotics application. In: 2017 24th International Conference on Mechatronics and Machine Vision in Practice (M2VIP), pp.\u00a01\u20136. IEEE (2017)","DOI":"10.1109\/M2VIP.2017.8211432"},{"key":"4_CR24","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes (2022)"},{"issue":"13","key":"4_CR25","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521\u20133526 (2017)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"4_CR26","unstructured":"Lee, C., Cho, K., Kang, W.: Mixout: effective regularization to finetune large-scale pretrained language models (2020)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"4_CR28","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":"4_CR29","doi-asserted-by":"crossref","unstructured":"Medeiros, H.R., Pena, F.A.G., Aminbeidokhti, M., Dubail, T., Granger, E., Pedersoli, M.: HalluciDet: hallucinating RGB modality for person detection through privileged information. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1444\u20131453 (2024)","DOI":"10.1109\/WACV57701.2024.00147"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Menezes, A.G., de\u00a0Moura, G., Alves, C., de\u00a0Carvalho, A.C.: Continual object detection: a review of definitions, strategies, and challenges. Neural Netw. (2023)","DOI":"10.1016\/j.neunet.2023.01.041"},{"key":"4_CR31","unstructured":"Minderer, M., Gritsenko, A., Houlsby, N.: Scaling open-vocabulary object detection. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"4_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/978-3-031-20080-9_42","volume-title":"Computer Vision \u2013 ECCV 2022","author":"M Minderer","year":"2022","unstructured":"Minderer, M., et al.: Simple open-vocabulary object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13670, pp. 728\u2013755. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_42"},{"issue":"1","key":"4_CR33","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1109\/TIV.2022.3185303","volume":"8","author":"O Natan","year":"2022","unstructured":"Natan, O., Miura, J.: End-to-end autonomous driving with semantic depth cloud mapping and multi-agent. IEEE Trans. Intell. Veh. 8(1), 557\u2013571 (2022)","journal-title":"IEEE Trans. Intell. Veh."},{"key":"4_CR34","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.patrec.2022.01.026","volume":"155","author":"MA \u00d6zkano\u011flu","year":"2022","unstructured":"\u00d6zkano\u011flu, M.A., Ozer, S.: InfraGAN: a GAN architecture to transfer visible images to infrared domain. Pattern Recogn. Lett. 155, 69\u201376 (2022)","journal-title":"Pattern Recogn. Lett."},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Pang, Y., Lin, J., Qin, T., Chen, Z.: Image-to-image translation: methods and applications (2021)","DOI":"10.1109\/TMM.2021.3109419"},{"key":"4_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/978-3-030-58545-7_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Park","year":"2020","unstructured":"Park, T., Efros, A.A., Zhang, R., Zhu, J.-Y.: Contrastive learning for unpaired image-to-image translation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 319\u2013345. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_19"},{"key":"4_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/978-3-030-58545-7_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Park","year":"2020","unstructured":"Park, T., Efros, A.A., Zhang, R., Zhu, J.-Y.: Contrastive learning for unpaired image-to-image translation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 319\u2013345. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_19"},{"issue":"16","key":"4_CR38","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1080\/01691864.2017.1365009","volume":"31","author":"HA Pierson","year":"2017","unstructured":"Pierson, H.A., Gashler, M.S.: Deep learning in robotics: a review of recent research. Adv. Robot. 31(16), 821\u2013835 (2017)","journal-title":"Adv. Robot."},{"key":"4_CR39","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR40","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"},{"issue":"1","key":"4_CR41","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1177\/0306312717741687","volume":"48","author":"J Stilgoe","year":"2018","unstructured":"Stilgoe, J.: Machine learning, social learning and the governance of self-driving cars. Soc. Stud. Sci. 48(1), 25\u201356 (2018)","journal-title":"Soc. Stud. Sci."},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Vasconcelos, C., Birodkar, V., Dumoulin, V.: Proper reuse of image classification features improves object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13628\u201313637 (2022)","DOI":"10.1109\/CVPR52688.2022.01326"},{"issue":"9","key":"4_CR44","doi-asserted-by":"publisher","first-page":"2020","DOI":"10.3390\/rs14092020","volume":"14","author":"Q Wang","year":"2022","unstructured":"Wang, Q., Chi, Y., Shen, T., Song, J., Zhang, Z., Zhu, Y.: Improving RGB-infrared object detection by reducing cross-modality redundancy. Remote Sens. 14(9), 2020 (2022)","journal-title":"Remote Sens."},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yang, E., Shen, L., Huang, H.: A comprehensive survey of forgetting in deep learning beyond continual learning (2023)","DOI":"10.1109\/TPAMI.2024.3498346"},{"key":"4_CR46","doi-asserted-by":"crossref","unstructured":"Wortsman, M., et\u00a0al.: Robust fine-tuning of zero-shot models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7959\u20137971 (2022)","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"4_CR47","unstructured":"Zhang, A., Lipton, Z.C., Li, M., Smola, A.J.: Dive into deep learning. arXiv preprint arXiv:2106.11342 (2021)"},{"key":"4_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, H., Fromont, E., Lef\u00e8vre, S., Avignon, B.: Multispectral fusion for object detection with cyclic fuse-and-refine blocks. In: 2020 IEEE International Conference on Image Processing (ICIP), pp. 276\u2013280. IEEE (2020)","DOI":"10.1109\/ICIP40778.2020.9191080"},{"key":"4_CR49","unstructured":"Zhang, T., Wu, F., Katiyar, A., Weinberger, K.Q., Artzi, Y.: Revisiting few-sample BERT fine-tuning (2021)"},{"key":"4_CR50","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"4_CR51","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"}],"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\/978-3-031-73024-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T17:04:17Z","timestamp":1732554257000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73024-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"ISBN":["9783031730238","9783031730245"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73024-5_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,24]]},"assertion":[{"value":"24 November 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"}}]}}