Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Yushu, Su, Yongyi, Goodge, Adam, Jia, Kui, Xu, Xun
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929735095812096
author Li, Yushu
Su, Yongyi
Goodge, Adam
Jia, Kui
Xu, Xun
author_facet Li, Yushu
Su, Yongyi
Goodge, Adam
Jia, Kui
Xu, Xun
contents Vision-language models (VLMs) have revolutionized machine learning by leveraging large pre-trained models to tackle various downstream tasks. Although label, training, and data efficiency have improved, many state-of-the-art VLMs still require task-specific hyperparameter tuning and fail to fully exploit test samples. To overcome these challenges, we propose a graph-based approach for label-efficient adaptation and inference. Our method dynamically constructs a graph over text prompts, few-shot examples, and test samples, using label propagation for inference without task-specific tuning. Unlike existing zero-shot label propagation techniques, our approach requires no additional unlabeled support set and effectively leverages the test sample manifold through dynamic graph expansion. We further introduce a context-aware feature re-weighting mechanism to improve task adaptation accuracy. Additionally, our method supports efficient graph expansion, enabling real-time inductive inference. Extensive evaluations on downstream tasks, such as fine-grained categorization and out-of-distribution generalization, demonstrate the effectiveness of our approach. The source code is available at https://github.com/Yushu-Li/ECALP.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18303
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model
Li, Yushu
Su, Yongyi
Goodge, Adam
Jia, Kui
Xu, Xun
Computer Vision and Pattern Recognition
Vision-language models (VLMs) have revolutionized machine learning by leveraging large pre-trained models to tackle various downstream tasks. Although label, training, and data efficiency have improved, many state-of-the-art VLMs still require task-specific hyperparameter tuning and fail to fully exploit test samples. To overcome these challenges, we propose a graph-based approach for label-efficient adaptation and inference. Our method dynamically constructs a graph over text prompts, few-shot examples, and test samples, using label propagation for inference without task-specific tuning. Unlike existing zero-shot label propagation techniques, our approach requires no additional unlabeled support set and effectively leverages the test sample manifold through dynamic graph expansion. We further introduce a context-aware feature re-weighting mechanism to improve task adaptation accuracy. Additionally, our method supports efficient graph expansion, enabling real-time inductive inference. Extensive evaluations on downstream tasks, such as fine-grained categorization and out-of-distribution generalization, demonstrate the effectiveness of our approach. The source code is available at https://github.com/Yushu-Li/ECALP.
title Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.18303