{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:48:20Z","timestamp":1773802100205,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"15","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>In this paper, we focus on Single-Domain Generalized Object Detection (Single-DGOD), aiming to transfer a detector trained on one source domain to multiple unknown domains.\nExisting methods for Single-DGOD typically rely on discrete data augmentation or static perturbation methods to expand data diversity, thereby mitigating the lack of access to target domain data. However, in real-world scenarios such as changes in weather or lighting conditions, domain shifts often occur continuously and gradually. \nDiscrete augmentations and static perturbations fail to effectively capture the dynamic variation of feature distributions, thereby limiting the model's ability to perceive fine-grained cross-domain differences.\nTo this end, we propose a new method, i.e., Liquid Temporal Feature Evolution, which simulates the progressive evolution of features from the source domain to simulated latent distributions by incorporating temporal modeling and liquid neural network\u2013driven parameter adjustment. Specifically, we introduce controllable Gaussian noise injection and multi-scale Gaussian blurring to simulate initial feature perturbations, followed by temporal modeling and a liquid parameter adjustment mechanism to generate adaptive modulation parameters, enabling a smooth and continuous adaptation across domains.\nBy capturing progressive cross-domain feature evolution and dynamically regulating adaptation paths, our method bridges the source-unknown domain distribution gap, significantly boosting generalization and robustness to unseen shifts.\nSignificant performance improvements on the Diverse Weather dataset and Real-to-Art benchmark demonstrate the superiority of our method.<\/jats:p>","DOI":"10.1609\/aaai.v40i15.38306","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:18:43Z","timestamp":1773793123000},"page":"13061-13069","source":"Crossref","is-referenced-by-count":0,"title":["Simulating Distribution Dynamics: Liquid Temporal Feature Evolution for Single-Domain Generalized Object Detection"],"prefix":"10.1609","volume":"40","author":[{"given":"Zihao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aming","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yahong","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38306\/42268","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38306\/42268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:18:44Z","timestamp":1773793124000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38306"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i15.38306","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}