{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T07:58:00Z","timestamp":1742975880776,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031824807"},{"type":"electronic","value":"9783031824814"}],"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\/978-3-031-82481-4_15","type":"book-chapter","created":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T15:44:13Z","timestamp":1741016653000},"page":"209-223","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Attention-Based Representation Distillation Baseline for\u00a0Multi-label Continual Learning"],"prefix":"10.1007","author":[{"given":"Martin","family":"Menabue","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanuele","family":"Frascaroli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matteo","family":"Boschini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lorenzo","family":"Bonicelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Angelo","family":"Porrello","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simone","family":"Calderara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,4]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Abdelsalam, M., Faramarzi, M., Sodhani, S., Chandar, S.: IIRC: incremental implicitly-refined classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01089"},{"key":"15_CR2","unstructured":"Aljundi, R., Lin, M., Goujaud, B., Bengio, Y.: Gradient based sample selection for online continual learning. In: Advances in Neural Information Processing Systems (2019)"},{"key":"15_CR3","unstructured":"Bonicelli, L., et al.: On the effectiveness of equivariant regularization for robust online continual learning. arXiv preprint arXiv:2305.03648 (2023)"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Boschini, M., et al.: Transfer without forgetting. In: Proceedings of the European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-20050-2_40"},{"key":"15_CR5","unstructured":"Buzzega, P., Boschini, M., Porrello, A., Abati, D., Calderara, S.: Dark experience for general continual learning: a strong, simple baseline. In: Advances in Neural Information Processing Systems (2020)"},{"key":"15_CR6","unstructured":"Caccia, L., Aljundi, R., Asadi, N., Tuytelaars, T., Pineau, J., Belilovsky, E.: New insights on reducing abrupt representation change in online continual learning. In: International Conference on Learning Representations Workshop (2022)"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Chaudhry, A., Dokania, P.K., Ajanthan, T., Torr, P.H.: Riemannian walk for incremental learning: understanding forgetting and intransigence. In: Proceedings of the European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"15_CR8","unstructured":"Chaudhry, A., Ranzato, M., Rohrbach, M., Elhoseiny, M.: Efficient lifelong learning with a-gem. In: International Conference on Learning Representations Workshop (2019)"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Chen, X., Cao, Q., Zhong, Y., Zhang, J., Gao, S., Tao, D.: Dearkd: data-efficient early knowledge distillation for vision transformers. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01174"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"De\u00a0Lange, M., et al.: A continual learning survey: defying forgetting in classification tasks. IEEE Trans. Pattern Anal. Mach. Intell. (2021)","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"15_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations Workshop (2021)"},{"key":"15_CR12","unstructured":"Farquhar, S., Gal, Y.: Towards robust evaluations of continual learning. In: International Conference on Learning Representations Workshop (2018)"},{"issue":"1","key":"15_CR13","first-page":"19","volume":"5","author":"D Ganda","year":"2018","unstructured":"Ganda, D., Buch, R.: A survey on multi label classification. Recent Trends Program. Lang. 5(1), 19\u201323 (2018)","journal-title":"Recent Trends Program. Lang."},{"key":"15_CR14","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 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"15_CR15","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: Neural Information Processing Systems Workshops (2015)"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Kim, C.D., Jeong, J., Kim, G.: Imbalanced continual learning with partitioning reservoir sampling. In: Proceedings of the European Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-58601-0_25"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. In: Proceedings of the National Academy of Sciences (2017)","DOI":"10.1073\/pnas.1611835114"},{"key":"15_CR18","unstructured":"Krizhevsky, A., et al.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009)"},{"key":"15_CR19","unstructured":"Li, W., Wang, L., Li, W., Agustsson, E., Van\u00a0Gool, L.: Webvision database: visual learning and understanding from web data. arXiv preprint arXiv:1708.02862 (2017)"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. (2017)","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Lin, S., et al.: Knowledge distillation via the target-aware transformer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01064"},{"key":"15_CR22","unstructured":"Lopez-Paz, D., Ranzato, M.: Gradient episodic memory for continual learning. In: Advances in Neural Information Processing Systems (2017)"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Psychology of Learning and Motivation (1989)","DOI":"10.1016\/S0079-7421(08)60536-8"},{"key":"15_CR24","unstructured":"Mehta, S.V., Patil, D., Chandar, S., Strubell, E.: An empirical investigation of the role of pre-training in lifelong learning. In: International Conference on Learning Representations Workshop (2022)"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Parisi, G.I., Kemker, R., Part, J.L., Kanan, C., Wermter, S.: Continual lifelong learning with neural networks: a review. Neural Netw. (2019)","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"15_CR26","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021)"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Rajeswar, S., Rodriguez, P., Singhal, S., Vazquez, D., Courville, A.: Multi-label iterated learning for image classification with label ambiguity. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00474"},{"key":"15_CR28","unstructured":"Ramasesh, V.V., Lewkowycz, A., Dyer, E.: Effect of scale on catastrophic forgetting in neural networks. In: International Conference on Learning Representations Workshop (2022)"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Ratcliff, R.: Connectionist models of recognition memory: constraints imposed by learning and forgetting functions. Psychol. Rev. (1990)","DOI":"10.1037\/\/0033-295X.97.2.285"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: ICARL: incremental classifier and representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.587"},{"issue":"2","key":"15_CR31","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1080\/09540099550039318","volume":"7","author":"A Robins","year":"1995","unstructured":"Robins, A.: Catastrophic forgetting, rehearsal and pseudorehearsal. Connection Sci. 7(2), 123\u2013146 (1995)","journal-title":"Connection Sci."},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Smith, J.S., et al.: Coda-prompt: continual decomposed attention-based prompting for rehearsal-free continual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"15_CR33","unstructured":"Sorower, M.S.: A literature survey on algorithms for multi-label learning. Oregon State University, Corvallis, vol. 18, no. 1, p. 25 (2010)"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Tarekegn, A.N., Giacobini, M., Michalak, K.: A review of methods for imbalanced multi-label classification. Pattern Recognit. (2021)","DOI":"10.1016\/j.patcog.2021.107965"},{"key":"15_CR35","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Van\u00a0de Ven, G.M., Tuytelaars, T., Tolias, A.S.: Three types of incremental learning. Nat. Mach. Intell. (2022)","DOI":"10.1038\/s42256-022-00568-3"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Vitter, J.S.: Random sampling with a reservoir. ACM Trans. Math. Softw. (1985)","DOI":"10.1145\/3147.3165"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Wang, J., Cao, M., Shi, S., Wu, B., Yang, Y.: Attention probe: vision transformer distillation in the wild. In: IEEE International Conference on Acoustics, Speech and Signal Processing (2022)","DOI":"10.1109\/ICASSP43922.2022.9747484"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Dualprompt: complementary prompting for rehearsal-free continual learning. In: Proceedings of the European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"15_CR40","unstructured":"Wang, Z., et al.: Learning to prompt for continual learning. In: Proceedings of the European Conference on Computer Vision (2022)"},{"key":"15_CR41","unstructured":"Yang, Z., Li, Z., Zeng, A., Li, Z., Yuan, C., Li, Y.: Vitkd: practical guidelines for VIT feature knowledge distillation. In: International Conference on Learning Representations Workshop (2023)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning, Optimization, and Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-82481-4_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T15:44:26Z","timestamp":1741016666000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-82481-4_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031824807","9783031824814"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-82481-4_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"4 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"LOD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning, Optimization, and Data Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Castiglione della Pescaia","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":"21 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mod2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lod2024.icas.events\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}