تقرير
FFF: Fixing Flawed Foundations in contrastive pre-training results in very strong Vision-Language models
| العنوان: | FFF: Fixing Flawed Foundations in contrastive pre-training results in very strong Vision-Language models |
|---|---|
| المؤلفون: | Bulat, Adrian, Ouali, Yassine, Tzimiropoulos, Georgios |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence |
| الوصف: | Despite noise and caption quality having been acknowledged as important factors impacting vision-language contrastive pre-training, in this paper, we show that the full potential of improving the training process by addressing such issues is yet to be realized. Specifically, we firstly study and analyze two issues affecting training: incorrect assignment of negative pairs, and low caption quality and diversity. Then, we devise effective solutions for addressing both problems, which essentially require training with multiple true positive pairs. Finally, we propose training with sigmoid loss to address such a requirement. We show very large gains over the current state-of-the-art for both image recognition ($\sim +6\%$ on average over 11 datasets) and image retrieval ($\sim +19\%$ on Flickr30k and $\sim +15\%$ on MSCOCO). Comment: Accepted at CVPR 2024 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2405.10286 |
| رقم الأكسشن: | edsarx.2405.10286 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |