Unsupervised Parameter Efficient Source-free Post-pretraining

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jha, Abhishek, Tuytelaars, Tinne, Asano, Yuki M.
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929735649460224
author Jha, Abhishek
Tuytelaars, Tinne
Asano, Yuki M.
author_facet Jha, Abhishek
Tuytelaars, Tinne
Asano, Yuki M.
contents Following the success in NLP, the best vision models are now in the billion parameter ranges. Adapting these large models to a target distribution has become computationally and economically prohibitive. Addressing this challenge, we introduce UpStep, an Unsupervised Parameter-efficient Source-free post-pretraining approach, designed to efficiently adapt a base model from a source domain to a target domain: i) we design a self-supervised training scheme to adapt a pretrained model on an unlabeled target domain in a setting where source domain data is unavailable. Such source-free setting comes with the risk of catastrophic forgetting, hence, ii) we propose center vector regularization (CVR), a set of auxiliary operations that minimize catastrophic forgetting and additionally reduces the computational cost by skipping backpropagation in 50\% of the training iterations. Finally iii) we perform this adaptation process in a parameter-efficient way by adapting the pretrained model through low-rank adaptation methods, resulting in a fraction of parameters to optimize. We utilize various general backbone architectures, both supervised and unsupervised, trained on Imagenet as our base model and adapt them to a diverse set of eight target domains demonstrating the adaptability and generalizability of our proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2502_21313
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unsupervised Parameter Efficient Source-free Post-pretraining
Jha, Abhishek
Tuytelaars, Tinne
Asano, Yuki M.
Computer Vision and Pattern Recognition
Machine Learning
Following the success in NLP, the best vision models are now in the billion parameter ranges. Adapting these large models to a target distribution has become computationally and economically prohibitive. Addressing this challenge, we introduce UpStep, an Unsupervised Parameter-efficient Source-free post-pretraining approach, designed to efficiently adapt a base model from a source domain to a target domain: i) we design a self-supervised training scheme to adapt a pretrained model on an unlabeled target domain in a setting where source domain data is unavailable. Such source-free setting comes with the risk of catastrophic forgetting, hence, ii) we propose center vector regularization (CVR), a set of auxiliary operations that minimize catastrophic forgetting and additionally reduces the computational cost by skipping backpropagation in 50\% of the training iterations. Finally iii) we perform this adaptation process in a parameter-efficient way by adapting the pretrained model through low-rank adaptation methods, resulting in a fraction of parameters to optimize. We utilize various general backbone architectures, both supervised and unsupervised, trained on Imagenet as our base model and adapt them to a diverse set of eight target domains demonstrating the adaptability and generalizability of our proposed approach.
title Unsupervised Parameter Efficient Source-free Post-pretraining
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2502.21313