Metraipolis › archive › dc_c2b587dca233

BPG: Balancing Plasticity and Generalization for Domain Incremental Learning — arXiv:2608.10804

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.10804
License (as archived): CC0-1.0
Archived: 2026-10-19T06:09:27.916Z
SHA-256 of the archived text: a09dd61ee66eb0d7d6add628ecb49349ce40394c8cf5d8e0218768b465d2b920
Stable URL of this page: https://metraipolis.com/documento/dc_c2b587dca233

How to cite

BPG: Balancing Plasticity and Generalization for Domain Incremental Learning — arXiv:2608.10804 — arXiv (en), https://arxiv.org/abs/2608.10804 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c2b587dca233 (Metraipolis archive dc_c2b587dca233, sha256 a09dd61ee66eb0d7d6add628ecb49349ce40394c8cf5d8e0218768b465d2b920)

BibTeX

@misc{dcc2b587dca233,
  title = {BPG: Balancing Plasticity and Generalization for Domain Incremental Learning — arXiv:2608.10804},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10804},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c2b587dca233; sha256 a09dd61ee66eb0d7d6add628ecb49349ce40394c8cf5d8e0218768b465d2b920},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10804. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep neural networks excel in various tasks but struggle to generalize across evolving data distributions, leading to significant performance degradation under domain shifts. Domain incremental learning (DIL) addresses this challenge by enabling models to continuously adapt while retaining prior knowledge. Among existing DIL approaches, the parameter-isolation paradigm achieves state-of-the-art performance. However, these methods often adopt a one-size-fits-all approach to adapt to new domains, resulting in either insufficient learning capacity or redundant parameters. In this work, we propose BPG, a unified framework that addresses both challenges through two complementary components: BPG-Adapter, which dynamically determines each domain's adapter hidden dimension based on domain-specific feature separability, and BPG-Inference, a soft domain mixture strategy that integrates multiple domain-specific models at test time, mitigating domain ID misselection. Experimental results on DomainNet, CDDB, and CORe50 demonstrate that BPG consistently outperforms uniform adapter-based approaches and hard domain selection strategies, achieving state-of-the-art average accuracy while reducing forgetting to as low as 0.22% on DomainNet.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.10804 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T05:57:28.405Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).