# BPG: Balancing Plasticity and Generalization for Domain Incremental Learning

arXiv: https://arxiv.org/abs/2608.10804 · HTML: https://mlsanity.com/paper/2608.10804/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 102 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.10512/) (2023)
- [On Tiny Episodic Memories in Continual Learning](https://mlsanity.com/paper/1902.10486/) (2019)
- [DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation](https://mlsanity.com/paper/2210.07558/) (2022)
- [Continual Learning and Catastrophic Forgetting](https://mlsanity.com/paper/2403.05175/) (2024)
- [Subspace Regularizers for Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2110.07059/) (2021)
- [Dynamic Integration of Task-Specific Adapters for Class Incremental Learning](https://mlsanity.com/paper/2409.14983/) (2024)
- [GeLoRA: Geometric Adaptive Ranks For Efficient LoRA Fine-tuning](https://mlsanity.com/paper/2412.09250/) (2024)
- [Variational Prototype Replays for Continual Learning](https://mlsanity.com/paper/1905.09447/) (2019)
- [Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery](https://mlsanity.com/paper/2507.04725/) (2025)
- [VDC-Agent: When Video Detailed Captioners Evolve Themselves via Agentic Self-Reflection](https://mlsanity.com/paper/2511.19436/) (2025)
- [Trajectory-Diversity-Driven Robust Vision-and-Language Navigation](https://mlsanity.com/paper/2603.15370/) (2026)
- [Beyond CLIP Generalization: Against Forward&Backward Forgetting Adapter for Continual Learning of Vision-Language Models](https://mlsanity.com/paper/2505.07690/) (2025)
- [Space Rotation with Basis Transformation for Training-free Test-Time Adaptation](https://mlsanity.com/paper/2502.19946/) (2025)
- [Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learning](https://mlsanity.com/paper/2503.00515/) (2025)
- [Continual Knowledge Consolidation LORA for Domain Incremental Learning](https://mlsanity.com/paper/2510.16077/) (2025)
- [LPT: Less-overfitting Prompt Tuning for Vision-Language Model](https://mlsanity.com/paper/2410.10247/) (2024)
- [Is Parameter Isolation Better for Prompt-Based Continual Learning?](https://mlsanity.com/paper/2601.20894/) (2026)
- [GFPL: Generative Federated Prototype Learning for Resource-Constrained and Data-Imbalanced Vision Task](https://mlsanity.com/paper/2602.21873/) (2026)

## Abstract (arXiv)

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.