# Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need

arXiv: https://arxiv.org/abs/2505.23744 · HTML: https://mlsanity.com/paper/2505.23744/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2025.

## Built on by (most cited first, 6 of 6)

- [Continual Knowledge Consolidation LORA for Domain Incremental Learning](https://mlsanity.com/paper/2510.16077/) (2025)
- [Unleashing the Potential of All Test Samples: Mean-Shift Guided Test-Time Adaptation](https://mlsanity.com/paper/2507.00462/) (2025)
- [Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection](https://mlsanity.com/paper/2607.17340/) (2026)
- [ContiGuard: A Framework for Continual Toxicity Detection Against Evolving Evasive Perturbations](https://mlsanity.com/paper/2603.14843/) (2026)
- [Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation](https://mlsanity.com/paper/2606.30190/) (2026)
- [Restoring Without Forgetting: Continual Learning Across Image Degradations](https://mlsanity.com/paper/2608.23799/) (2026)

## Abstract (arXiv)

Deep neural networks (DNNs) often underperform in real-world, dynamic settings where data distributions change over time. Domain Incremental Learning (DIL) offers a solution by enabling continual model adaptation, with Parameter-Isolation DIL (PIDIL) emerging as a promising paradigm to reduce knowledge conflicts. However, existing PIDIL methods struggle with parameter selection accuracy, especially as the number of domains and corresponding classes grows. To address this, we propose SOYO, a lightweight framework that improves domain selection in PIDIL. SOYO introduces a Gaussian Mixture Compressor (GMC) and Domain Feature Resampler (DFR) to store and balance prior domain data efficiently, while a Multi-level Domain Feature Fusion Network (MDFN) enhances domain feature extraction. Our framework supports multiple Parameter-Efficient Fine-Tuning (PEFT) methods and is validated across tasks such as image classification, object detection, and speech enhancement. Experimental results on six benchmarks demonstrate SOYO's consistent superiority over existing baselines, showcasing its robustness and adaptability in complex, evolving environments. The codes will be released in https://github.com/qwangcv/SOYO.