English

Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Tasks

Computer Vision and Pattern Recognition 2023-07-14 v1

Abstract

Vision-language foundation models such as CLIP have shown impressive zero-shot performance on many tasks and datasets, especially thanks to their free-text inputs. However, they struggle to handle some downstream tasks, such as fine-grained attribute detection and localization. In this paper, we propose a multitask fine-tuning strategy based on a positive/negative prompt formulation to further leverage the capacities of the vision-language foundation models. Using the CLIP architecture as baseline, we show strong improvements on bird fine-grained attribute detection and localization tasks, while also increasing the classification performance on the CUB200-2011 dataset. We provide source code for reproducibility purposes: it is available at https://github.com/FactoDeepLearning/MultitaskVLFM.

Keywords

Cite

@article{arxiv.2307.06795,
  title  = {Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Tasks},
  author = {Denis Coquenet and Clément Rambour and Emanuele Dalsasso and Nicolas Thome},
  journal= {arXiv preprint arXiv:2307.06795},
  year   = {2023}
}
R2 v1 2026-06-28T11:29:29.086Z