{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T15:19:38Z","timestamp":1758122378236,"version":"3.27.0"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643685489","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,16]]},"abstract":"<jats:p>Continual learning is referred to as machine learning model\u2019s ability to learn a sequence of tasks or data over time without forgetting previously learned knowledge. In particular, we focus on domain incremental learning where the model trained on one domain, e.g., real-life photos, has to be augmented to accommodate data from new domains, e.g., cartoon images. Typical incremental learning relies on rehearsal-based methods, which store trained samples in a buffer and replay them during training alongside new data. This results in significant memory overhead and raise concerns about data privacy. Recently, prompt-based methods address these challenges and outperform them by utilizing the pre-trained Vision Transformer (ViT) and replacing the replay buffer with a prompt pool. However, existing prompt-based models fail to capture domain-specific knowledge and perform poorly in domain incremental learning. In this paper, we propose \u201cdomain prompt incremental learning via dynamic neural network\u201d, which combines the advantages of architecture-based and prompt-based methods. Specifically, our framework maintains two types of prompt: a instance-level prompt that improves the model\u2019s generalization ability is shared across all input samples; and a domain prompt that encodes domain-specific knowledge is assigned for each task. Furthermore, a separated classification head is trained for each domain so that the model has a pre-trained ViT and an ensemble of classification layers, one for each domain. The experimental results shows that our approach outperforms state-of-the-art methods by 2.3% in average on two domain incremental learning (DIL) benchmarks.<\/jats:p>","DOI":"10.3233\/faia240547","type":"book-chapter","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T12:48:52Z","timestamp":1729169332000},"source":"Crossref","is-referenced-by-count":1,"title":["Prompt-Based Domain Incremental Learning with Modular Classification Layer"],"prefix":"10.3233","author":[{"given":"Boyu","family":"Wang","sequence":"first","affiliation":[{"name":"Dept. of Electrical Engineering and Computer Science, Syracuse University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Ma","sequence":"additional","affiliation":[{"name":"Dept. of Electrical Engineering and Computer Science, Syracuse University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinru","family":"Qiu","sequence":"additional","affiliation":[{"name":"Dept. of Electrical Engineering and Computer Science, Syracuse University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2024"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA240547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T12:48:53Z","timestamp":1729169333000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA240547"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"ISBN":["9781643685489"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia240547","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,16]]}}}