Papers › CAPIVARA: Cost-Efficient Approach for Improving Multilingual CLIP Performance on...

CAPIVARA: Cost-Efficient Approach for Improving Multilingual CLIP Performance on Low-Resource Languages

20 Oct 2023arXiv:2310.13683archive 2025-07-28

Gabriel Oliveira dos Santos, Diego A. B. Moreira, Alef Iury Ferreira, Jhessica Silva, Luiz Pereira, Pedro Bueno, Thiago Sousa, Helena Maia, Nádia Da Silva, Esther Colombini, Helio Pedrini, Sandra Avila

This work introduces CAPIVARA, a cost-efficient framework designed to enhance the performance of multilingual CLIP models in low-resource languages. While CLIP has excelled in zero-shot vision-language tasks, the resource-intensive nature of model training remains challenging. Many datasets lack linguistic diversity, featuring solely English descriptions for images. CAPIVARA addresses this by augmenting text data using image captioning and machine translation to generate multiple synthetic captions in low-resource languages. We optimize the training pipeline with LiT, LoRA, and gradient checkpointing to alleviate the computational cost. Through extensive experiments, CAPIVARA emerges as state of the art in zero-shot tasks involving images and Portuguese texts. We show the potential for significant improvements in other low-resource languages, achieved by fine-tuning the pre-trained multilingual CLIP using CAPIVARA on a single GPU for 2 hours. Our model and code is available at https://github.com/hiaac-nlp/CAPIVARA.

PaperPDFCode

Code

hiaac-nlp/capivara officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DiversityImage CaptioningMachine Translation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIPGradient Checkpointing

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections