paper-with-me

홈 › Papers

Block-wise LoRA: Revisiting Fine-grained LoRA for Effective Personalization and Stylization in Text-to-Image Generation

2024-03-12 · Likun Li, Haoqi Zeng, Changpeng Yang, Haozhe Jia, Di Xu

The objective of personalization and stylization in text-to-image is to instruct a pre-trained diffusion model to analyze new concepts introduced by users and incorporate them into expected styles. Recently, parameter-efficient fine-tuning (PEFT) approaches have been widely adopted to address this task and have greatly propelled the development of this field. Despite their popularity, existing efficient fine-tuning methods still struggle to achieve effective personalization and stylization in T2I generation. To address this issue, we propose block-wise Low-Rank Adaptation (LoRA) to perform fine-grained fine-tuning for different blocks of SD, which can generate images faithful to input prompts and target identity and also with desired style. Extensive experiments demonstrate the effectiveness of the proposed method.

📄 PDF Abstract BibTeX arXiv:2403.07500

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generationparameter-efficient fine-tuningText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-Task Learning

2025-01-25 · Ziyu Zhao, Yixiao Zhou, Didi Zhu, Tao Shen 외

Low-Rank Adaptation (LoRA) is widely used for adapting large language models (LLMs) to specific domains due to its efficiency and modularity. Meanwhile, vanilla LoRA struggles with task conflicts in multi-task scenarios.…

Mixture-of-ExpertsMulti-Task Learning

LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-design

2024-05-28 · Rui Kong, Qiyang Li, Xinyu Fang, Qingtian Feng 외

Recent literature has found that an effective method to customize or further improve large language models (LLMs) is to add dynamic adapters, such as low-rank adapters (LoRA) with Mixture-of-Experts (MoE) structures. Tho…

Mixture-of-Experts

Blockwise Adaptivity: Faster Training and Better Generalization in Deep Learning

2019-05-23 · Shuai Zheng, James T. Kwok

Stochastic methods with coordinate-wise adaptive stepsize (such as RMSprop and Adam) have been widely used in training deep neural networks. Despite their fast convergence, they can generalize worse than stochastic gradi…

Deep Learning

Learning Deep Bilinear Transformation for Fine-grained Image Representation

2019-11-09 · NeurIPS 2019 12 · Heliang Zheng, Jianlong Fu, Zheng-Jun Zha, Jiebo Luo

Bilinear feature transformation has shown the state-of-the-art performance in learning fine-grained image representations. However, the computational cost to learn pairwise interactions between deep feature channels is p…

Fine-Grained Image Recognition

FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning

2026-02-27 · Jieming Bian, Lei Wang, Letian Zhang, Jie Xu arxiv

Federated Learning (FL) with Low-Rank Adaptation (LoRA) has become a standard for privacy-preserving LLM fine-tuning. However, existing personalized methods predominantly operated under a restrictive Flat-Model Assumptio…

Federated Learning