Scalable Visual Attribute Recognition in E-Commerce Products via Automated Synthetic Label Generation
This work introduces a scalable approach that uses CLIP models to automatically generate synthetic labeled datasets, significantly reducing the need for manual annotation and demonstrates that synthetic labeling with vision-language models could serve as a practical and effective approach for large-scale visual attribu...
V. Martinez, V. Negri, Brayan Impata et al.
· 0 citations