{"type":"ScholarlyArticle","title":"DM-POSA: Enhancing Open-World Test-Time Adaptation with Dual-Mode Matching and Prompt-Based Open Set Adaptation","authors":[{"name":"Shiji Zhao","slug":"shiji-zhao","given":"Shiji","family":"Zhao","affiliation":""},{"name":"Shao-Yuan Li","slug":"shao-yuan-li","given":"Shao-Yuan","family":"Li","affiliation":""},{"name":"Chuanxing Geng","slug":"chuanxing-geng","given":"Chuanxing","family":"Geng","affiliation":""},{"name":"Sheng-Jun Huang","slug":"sheng-jun-huang","given":"Sheng-Jun","family":"Huang","affiliation":""},{"name":"Songcan Chen","slug":"songcan-chen","given":"Songcan","family":"Chen","affiliation":""}],"abstract":"The need to generalize the pre-trained deep learning models to unknown test-time data distributions has spurred research into test-time adaptation (TTA). Existing studies have mainly focused\r\n on closed-set TTA with only covariate shifts, while largely overlooking open-set TTA that involves semantic shifts, i.e., unknown open-set classes. However, addressing adaptation to unknown classes is crucial for open-world safety-critical applications such as autonomous driving. In this paper, we emphasize that accurate identification of the open-set samples is rather challenging in TTA. The entanglement of semantic shift and covariate shift mutually confuse the network’s discriminative capability. This co-interference further exacerbates considering the single-pass data nature and low latency requirements. With this under standing, we propose Dual-mode Matching and Prompt-based Open Set Adaptation (DM-POSA) for open-set TTA to enhance discriminative feature learning and unknown classes distinguishment with minimal time cost. DM-POSA identifies open-set samples via dual-mode matching strategies, including model-parameter-based and feature space-based matching. It also optimizes the model with a random pairing discrepancy loss, enhancing the distributional difference between open-set and closed-set samples, thus improving the model’s ability to recognize unknown categories. Extensive\r\n experiments show the superiority of DM-POSA over state-of-the-art baselines on both closed-set class adaptation and open-set class detection.","doi":"10.24963/ijcai.2025/790","url":"https://ijcai.org/proceedings/2025/790","pdf":"https://ijcai.org/proceedings/2025/0790.pdf","markdown":"https://ijcai.org/proceedings/2025/790.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/790","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Machine Learning","track":"Main Track","number":790,"pages":{"first":7101,"last":7109},"keywords":["Machine Learning: ML: Multi-task and transfer learning","Computer Vision: CV: Transfer, low-shot, semi- and un- supervised learning","Machine Learning: ML: Open-World/Open-Set/OOD Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}