{"ID":2823757,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.24922","arxiv_id":"2512.24922","title":"Semi-Supervised Diversity-Aware Domain Adaptation for 3D Object detection","abstract":"3D object detectors are fundamental components of perception systems in autonomous vehicles. While these detectors achieve remarkable performance on standard autonomous driving benchmarks, they often struggle to generalize across different domains - for instance, a model trained in the U.S. may perform poorly in regions like Asia or Europe. This paper presents a novel lidar domain adaptation method based on neuron activation patterns, demonstrating that state-of-the-art performance can be achieved by annotating only a small, representative, and diverse subset of samples from the target domain if they are correctly selected. The proposed approach requires very small annotation budget and, when combined with post-training techniques inspired by continual learning prevent weight drift from the original model. Empirical evaluation shows that the proposed domain adaptation approach outperforms both linear probing and state-of-the-art domain adaptation techniques.","short_abstract":"3D object detectors are fundamental components of perception systems in autonomous vehicles. While these detectors achieve remarkable performance on standard autonomous driving benchmarks, they often struggle to generalize across different domains - for instance, a model trained in the U.S. may perform poorly in region...","url_abs":"https://arxiv.org/abs/2512.24922","url_pdf":"https://arxiv.org/pdf/2512.24922v1","authors":"[\"Bartłomiej Olber\",\"Jakub Winter\",\"Paweł Wawrzyński\",\"Andrii Gamalii\",\"Daniel Górniak\",\"Marcin Łojek\",\"Robert Nowak\",\"Krystian Radlak\"]","published":"2025-12-31T15:26:09Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}