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.
@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}
}