# Improving Captioning for Low-Resource Languages by Cycle Consistency

arXiv: https://arxiv.org/abs/1908.07810 · HTML: https://mlsanity.com/paper/1908.07810/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2019.

## Built on by (most cited first, 3 of 3)

- [VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning](https://mlsanity.com/paper/2102.10407/) (2021)
- [Object-Centric Unsupervised Image Captioning](https://mlsanity.com/paper/2112.00969/) (2021)
- [Large Multimodal Models for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2502.05568/) (2025)

## Abstract (arXiv)

Improving the captioning performance on low-resource languages by leveraging English caption datasets has received increasing research interest in recent years. Existing works mainly fall into two categories: translation-based and alignment-based approaches. In this paper, we propose to combine the merits of both approaches in one unified architecture. Specifically, we use a pre-trained English caption model to generate high-quality English captions, and then take both the image and generated English captions to generate low-resource language captions. We improve the captioning performance by adding the cycle consistency constraint on the cycle of image regions, English words, and low-resource language words. Moreover, our architecture has a flexible design which enables it to benefit from large monolingual English caption datasets. Experimental results demonstrate that our approach outperforms the state-of-the-art methods on common evaluation metrics. The attention visualization also shows that the proposed approach really improves the fine-grained alignment between words and image regions.