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

TL;DR

This paper introduces SOYO, a lightweight framework that significantly improves parameter selection in Domain Incremental Learning by using novel modules, leading to better performance across various tasks and benchmarks.

Contribution

The paper presents SOYO, a new framework with GMC, DFR, and MDFN modules that enhances domain selection accuracy and supports multiple PEFT methods in DIL.

Findings

SOYO outperforms existing baselines on six benchmarks.

The framework demonstrates robustness across image, object detection, and speech tasks.

Experimental results show improved domain adaptation in complex environments.

Abstract

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.