Empowering Source-Free Domain Adaptation via MLLM-Guided Reliability-Based Curriculum Learning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Dongjie, Patwari, Kartik, Lai, Zhengfeng, Zhu, Xiaoguang, Cheung, Sen-ching, Chuah, Chen-Nee
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914234417283072
author Chen, Dongjie
Patwari, Kartik
Lai, Zhengfeng
Zhu, Xiaoguang
Cheung, Sen-ching
Chuah, Chen-Nee
author_facet Chen, Dongjie
Patwari, Kartik
Lai, Zhengfeng
Zhu, Xiaoguang
Cheung, Sen-ching
Chuah, Chen-Nee
contents Existing SFDA methods struggle to fully use pre-trained knowledge and often rely on a single model's predictions or handcrafted prompts, limiting robustness under domain shift. Multimodal Large Language Models (MLLMs) offer a promising alternative: they encode rich visual-semantic knowledge and generalize well without task-specific tuning. However, their use in SFDA is hindered by instruction-following failures, inconsistent outputs, and high inference costs. We propose Reliability-based Curriculum Learning (RCL), a novel framework that distills robust supervision from multiple frozen MLLMs into a compact target model. RCL organizes adaptation as a three-stage curriculum that progressively incorporates pseudo-labels based on inter-model agreement and model confidence, enabling stable and noise-aware training. Our approach achieves state-of-the-art performance on standard SFDA datasets, Office-Home, DomainNet-126, and VisDA-C, outperforming zero-shot MLLMs, their ensembles, all without accessing source data or tuning foundation models. Our code is available at: https://github.com/Dong-Jie-Chen/RCL.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18376
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Empowering Source-Free Domain Adaptation via MLLM-Guided Reliability-Based Curriculum Learning
Chen, Dongjie
Patwari, Kartik
Lai, Zhengfeng
Zhu, Xiaoguang
Cheung, Sen-ching
Chuah, Chen-Nee
Machine Learning
Computer Vision and Pattern Recognition
Existing SFDA methods struggle to fully use pre-trained knowledge and often rely on a single model's predictions or handcrafted prompts, limiting robustness under domain shift. Multimodal Large Language Models (MLLMs) offer a promising alternative: they encode rich visual-semantic knowledge and generalize well without task-specific tuning. However, their use in SFDA is hindered by instruction-following failures, inconsistent outputs, and high inference costs. We propose Reliability-based Curriculum Learning (RCL), a novel framework that distills robust supervision from multiple frozen MLLMs into a compact target model. RCL organizes adaptation as a three-stage curriculum that progressively incorporates pseudo-labels based on inter-model agreement and model confidence, enabling stable and noise-aware training. Our approach achieves state-of-the-art performance on standard SFDA datasets, Office-Home, DomainNet-126, and VisDA-C, outperforming zero-shot MLLMs, their ensembles, all without accessing source data or tuning foundation models. Our code is available at: https://github.com/Dong-Jie-Chen/RCL.
title Empowering Source-Free Domain Adaptation via MLLM-Guided Reliability-Based Curriculum Learning
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.18376