Abstract
Domain Generalized Semantic Segmentation (DGSS) aims to maintain robust performance across unseen target domains. Vision Foundation Models (VFMs) offer rich multi-domain knowledge that can enhance generalization. However, strategies for actively exploiting the rich subspace structures within VFMs remain under-explored, with many existing methods focusing primarily on preserving pre-trained knowledge. Furthermore, their LoRA components often suffer from limited representational diversity and inefficient parameter utilization. We propose RecycleLoRA, which addresses both challenges by employing Rank-Revealing QR Decomposition (RRQR) to systematically exploit VFM's subspace structures and enhance LoRA's representational richness. Our main adapter leverages minor subspace directions identified by RRQR to learn diverse and independent features, achieving competitive performance even when used alone. We further introduce a sub adapter that carefully refines major directions with minimal adjustments, providing complementary improvements to the main adapter's strong baseline performance. This design enables the dual adapters to learn distinct representations without requiring additional regularization losses. Our systematic exploitation of pre-trained subspace structures through RRQR-based initialization leads to superior domain generalization performance. RecycleLoRA achieves state-of-the-art performance on both synthetic-to-real generalization and real-to-real generalization tasks without complex architectures or additional inference latency.
Abstract (translated)
域泛化语义分割（DGSS）旨在使模型在未见过的目标域中保持稳健性能。视觉基础模型（VFMs）提供了丰富的多领域知识以增强泛化能力。然而，主动利用VFMs中丰富子空间结构的策略尚未得到充分探索，现有方法多侧重于保留预训练知识。此外，其LoRA组件常面临表征多样性有限与参数利用效率低的问题。我们提出RecycleLoRA，通过采用秩揭示QR分解（RRQR）系统性地挖掘VFM的子空间结构并增强LoRA的表征丰富度，从而同时解决上述挑战。主适配器利用RRQR识别的次要子空间方向学习多样且独立的特征，即使单独使用也能达到具有竞争力的性能。我们进一步引入子适配器，以最小调整精细优化主要方向，为主适配器的强基线性能提供互补提升。该设计使双适配器无需额外正则化损失即可学习差异化表征。通过基于RRQR的初始化系统利用预训练子空间结构，我们实现了更优的域泛化性能。RecycleLoRA在合成到真实泛化与真实到真实泛化任务上均达到最先进水平，且无需复杂架构或增加推理延迟。
URL
https://arxiv.org/abs/2603.28142
