BPG: Balancing Plasticity and Generalization for Domain Incremental Learning

• URL: http://arxiv.org/abs/2608.10804v1
• Date: Tue, 11 Aug 2026 11:22:27 GMT
• Title: BPG: Balancing Plasticity and Generalization for Domain Incremental Learning
• Abstract summary: Domain incremental learning enables models to continuously adapt while retaining prior knowledge.<n>We propose BPG, a unified framework that addresses both challenges through two complementary components.<n>BPG consistently outperforms uniform adapter-based approaches and hard domain selection strategies.
• Score: 48.68747632195046
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• DOME: Learning Transferable Domain Variables from Sparse Supervision for Test-Time Adaptation [61.70497741321102]
  Test-time adaptation aims to align a model to shifting test domains using only unlabeled streaming data.<n>Most existing methods implicitly infer a single global domain distribution, ignoring the multidimensional and sample-specific nature of real-world domain shifts.<n>We propose DOME, an effective domain encoder that explicitly models each sample's domain in a zero-shot manner.
  arXiv  Detail & Related papers  (2026-06-02T03:24:03Z)
• Unsupervised Multi-Source Federated Domain Adaptation under Domain Diversity through Group-Wise Discrepancy Minimization [2.522791298432536]
  Unsupervised multi-source domain adaptation (UMDA) aims to learn models that generalize to an unlabeled target domain by leveraging labeled data from multiple, diverse source domains.<n>We propose GALA, a scalable and robust federated UMDA framework that introduces two key components.<n>GALA consistently achieves competitive or state-of-the-art results on standard benchmarks and significantly outperforms prior methods in diverse multi-source settings.
  arXiv  Detail & Related papers  (2025-10-09T12:34:37Z)
• Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation [86.02485817444216]
  We introduce Multi-Prompt Alignment (MPA), a simple yet efficient framework for multi-source UDA. MPA denoises the learned prompts through an auto-encoding process and aligns them by maximizing the agreement of all the reconstructed prompts. Experiments show that MPA achieves state-of-the-art results on three popular datasets with an impressive average accuracy of 54.1% on DomainNet.
  arXiv  Detail & Related papers  (2022-09-30T03:40:10Z)
• Adaptive Domain Generalization via Online Disagreement Minimization [17.215683606365445]
  Domain Generalization aims to safely transfer a model to unseen target domains. AdaODM adaptively modifies the source model at test time for different target domains. Results show AdaODM stably improves the generalization capacity on unseen domains.
  arXiv  Detail & Related papers  (2022-08-03T11:51:11Z)
• TDACNN: Target-domain-free Domain Adaptation Convolutional Neural Network for Drift Compensation in Gas Sensors [6.451060076703026]
  In this paper, deep learning based on a target-domain-free domain adaptation convolutional neural network (TDACNN) is proposed. The main concept is that CNNs extract not only the domain-specific features of samples but also the domain-invariant features underlying both the source and target domains. Experiments on two datasets drift under different settings demonstrate the superiority of TDACNN compared with several state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-10-14T16:30:17Z)
• Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images [93.50240389540252]
  Road segmentation from remote sensing images is a challenging task with wide ranges of application potentials. We propose a novel stagewise domain adaptation model called RoadDA to address the domain shift (DS) issue in this field. Experiment results on two benchmarks demonstrate that RoadDA can efficiently reduce the domain gap and outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-08-28T09:29:14Z)
• Dynamic Domain Adaptation for Efficient Inference [12.713628738434881]
  Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain. Most prior DA approaches leverage complicated and powerful deep neural networks to improve the adaptation capacity. We propose a dynamic domain adaptation (DDA) framework, which can simultaneously achieve efficient target inference in low-resource scenarios.
  arXiv  Detail & Related papers  (2021-03-26T08:53:16Z)
• Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptation [66.74638960925854]
  Partial domain adaptation (PDA) deals with a realistic and challenging problem when the source domain label space substitutes the target domain. We propose an Adaptively-Accumulated Knowledge Transfer framework (A$2$KT) to align the relevant categories across two domains.
  arXiv  Detail & Related papers  (2020-08-27T00:53:43Z)
• Domain Conditioned Adaptation Network [90.63261870610211]
  We propose a Domain Conditioned Adaptation Network (DCAN) to excite distinct convolutional channels with a domain conditioned channel attention mechanism. This is the first work to explore the domain-wise convolutional channel activation for deep DA networks.
  arXiv  Detail & Related papers  (2020-05-14T04:23:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.