IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages

TL;DR

IGLUE is a comprehensive multilingual vision-and-language benchmark that evaluates transfer learning across 20 languages, highlighting the challenges and factors influencing model performance in zero-shot and few-shot settings.

Contribution

The paper introduces IGLUE, the first extensive multilingual benchmark for vision-and-language tasks, enabling evaluation of transfer learning across diverse languages and tasks.

Findings

Translate-test transfer outperforms zero-shot transfer.

Few-shot learning remains challenging for many tasks.

Performance correlates with unlabelled textual data availability.

Abstract

Reliable evaluation benchmarks designed for replicability and comprehensiveness have driven progress in machine learning. Due to the lack of a multilingual benchmark, however, vision-and-language research has mostly focused on English language tasks. To fill this gap, we introduce the Image-Grounded Language Understanding Evaluation benchmark. IGLUE brings together - by both aggregating pre-existing datasets and creating new ones - visual question answering, cross-modal retrieval, grounded reasoning, and grounded entailment tasks across 20 diverse languages. Our benchmark enables the evaluation of multilingual multimodal models for transfer learning, not only in a zero-shot setting, but also in newly defined few-shot learning setups. Based on the evaluation of the available state-of-the-art models, we find that translate-test transfer is superior to zero-shot transfer and that few-shot learning is hard to harness for many tasks. Moreover, downstream performance is partially explained by the amount of available unlabelled textual data for pretraining, and only weakly by the typological distance of target-source languages. We hope to encourage future research efforts in this area by releasing the benchmark to the community.