RecycleLoRA: Rank-Revealing QR-Based Dual-LoRA Subspace Adaptation for Domain Generalized Semantic Segmentation

• URL: http://arxiv.org/abs/2603.28142v1
• Date: Mon, 30 Mar 2026 08:05:39 GMT
• Title: RecycleLoRA: Rank-Revealing QR-Based Dual-LoRA Subspace Adaptation for Domain Generalized Semantic Segmentation
• Abstract summary: Vision Foundation Models (VFMs) offer rich multi-domain knowledge that can enhance generalization.<n>Existing strategies for actively exploiting the rich subspace structures within VFMs remain under-explored.<n>We propose RecycleLoRA, which employs Rank-Revealing QR Decomposition (RRQR) to systematically exploit VFM's subspace structures.
• Score: 8.041397263753709
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• RMAdapter: Reconstruction-based Multi-Modal Adapter for Vision-Language Models [36.97549106050972]
  We introduce a novel Reconstruction-based Multimodal Adapter (RMAdapter)<n> RMAdapter consists of: (1) an adaptation branch that injects task-specific knowledge through parameter-efficient fine-tuning, and (2) a reconstruction branch that preserves general knowledge by reconstructing latent space features back into the original feature space.<n>By computing reconstruction loss locally at each layer and sharing projection modules, the overall computational overhead is kept minimal.
  arXiv  Detail & Related papers  (2025-12-07T12:04:46Z)
• $\text{R}^2\text{R}$: A Route-to-Rerank Post-Training Framework for Multi-Domain Decoder-Only Rerankers [14.52446670807422]
  We introduce R2R, a domain-aware framework that combines dynamic expert routing with a two-stage training strategy.<n>To efficiently activate domain experts, R2R employs a lightweight Latent Semantic Router.<n>Our results confirm that R2R is a model-agnostic and modular approach to domain specialization with strong cross-domain robustness.
  arXiv  Detail & Related papers  (2025-11-25T06:54:51Z)
• Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution [76.66229730098759]
  In real-world image super-resolution (Real-ISR), existing approaches mainly rely on fine-tuning pre-trained diffusion models.<n>We propose a Mixture-of-Ranks (MoR) architecture for single-step image super-resolution.<n>We introduce a fine-grained expert partitioning strategy that treats each rank in LoRA as an independent expert.
  arXiv  Detail & Related papers  (2025-11-20T04:11:44Z)
• HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization [39.23407996213986]
  Low-Rank Adaptation (LoRA) has emerged as a widely used technique for adapting large language models to new domains.<n>Existing methods often rely on explicit task labels or additional training, which are impractical for deployment.<n>We propose textttHiLoRA, a training-free framework that performs adaptive hierarchical routing over LoRA pools.
  arXiv  Detail & Related papers  (2025-10-14T08:19:13Z)
• Domain-Specific Data Generation Framework for RAG Adaptation [58.20906914537952]
  Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning power of large language models with external retrieval to enable domain-grounded responses.<n>We propose RAGen, a framework for generating domain-grounded question-answer-context (QAC) triples tailored to diverse RAG adaptation approaches.
  arXiv  Detail & Related papers  (2025-10-13T09:59:49Z)
• GENRE-CMR: Generalizable Deep Learning for Diverse Multi-Domain Cardiac MRI Reconstruction [0.8749675983608171]
  We propose GENRE-CMR, a generative adversarial network (GAN)-based architecture to enhance reconstruction fidelity and generalization.<n>Experiments confirm that GENRE-CMR surpasses state-of-the-art methods on training and unseen data, achieving 0.9552 SSIM and 38.90 dB PSNR on unseen distributions.<n>Our framework presents a unified and robust solution for high-quality CMR reconstruction, paving the way for clinically adaptable deployment across heterogeneous acquisition protocols.
  arXiv  Detail & Related papers  (2025-08-28T09:43:59Z)
• Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains [92.36624674516553]
  Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs)<n>We investigate the effectiveness and scalability of RLVR across diverse real-world domains including medicine, chemistry, psychology, economics, and education.<n>We utilize a generative scoring technique that yields soft, model-based reward signals to overcome limitations posed by binary verifications.
  arXiv  Detail & Related papers  (2025-03-31T08:22:49Z)
• Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models [55.51408151807268]
  When tailored to specific domains, Large Language Models (LLMs) tend to experience catastrophic forgetting. crafting a versatile model for multiple domains simultaneously often results in a decline in overall performance. We present the RolE Prompting Guided Multi-Domain Adaptation (REGA) strategy.
  arXiv  Detail & Related papers  (2024-03-05T08:22:41Z)
• Specificity-Preserving Federated Learning for MR Image Reconstruction [94.58912814426122]
  Federated learning can be used to improve data privacy and efficiency in magnetic resonance (MR) image reconstruction. Recent FL techniques tend to solve this by enhancing the generalization of the global model. We propose a specificity-preserving FL algorithm for MR image reconstruction (FedMRI)
  arXiv  Detail & Related papers  (2021-12-09T22:13:35Z)
• Feature Alignment and Restoration for Domain Generalization and Adaptation [93.39253443415392]
  Cross domain feature alignment has been widely explored to pull the feature distributions of different domains in order to learn domain-invariant representations. We propose a unified framework termed Feature Alignment and Restoration (FAR) to simultaneously ensure high generalization and discrimination power of the networks. Experiments on multiple classification benchmarks demonstrate the high performance and strong generalization of our FAR framework for both domain generalization and unsupervised domain adaptation.
  arXiv  Detail & Related papers  (2020-06-22T05:08:13Z)

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.