# NLLB-CLIP -- train performant multilingual image retrieval model on a budget

arXiv: https://arxiv.org/abs/2309.01859 · HTML: https://mlsanity.com/paper/2309.01859/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 31 references that are in the map.
- First posted on arXiv 4 Sep 2023.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [Symbolic Discovery of Optimization Algorithms](https://mlsanity.com/paper/2302.06675/) (2023)
- [8-bit Optimizers via Block-wise Quantization](https://mlsanity.com/paper/2110.02861/) (2021)
- [Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages](https://mlsanity.com/paper/2010.02353/) (2020)
- [CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2212.09506/) (2022)
- [Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese](https://mlsanity.com/paper/2211.01335/) (2022)
- [Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset](https://mlsanity.com/paper/2205.12522/) (2022)
- [Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases](https://mlsanity.com/paper/2303.14742/) (2023)
- [AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities](https://mlsanity.com/paper/2211.06679/) (2022)
- [COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval](https://mlsanity.com/paper/1805.08661/) (2018)
- [CLIP model is an Efficient Continual Learner](https://mlsanity.com/paper/2210.03114/) (2022)
- [STAIR Captions: Constructing a Large-Scale Japanese Image Caption Dataset](https://mlsanity.com/paper/1705.00823/) (2017)
- [Towards Zero-shot Cross-lingual Image Retrieval](https://mlsanity.com/paper/2012.05107/) (2020)
- [Adapting CLIP For Phrase Localization Without Further Training](https://mlsanity.com/paper/2204.03647/) (2022)
- [Contrastive Language-Image Pre-training for the Italian Language](https://mlsanity.com/paper/2108.08688/) (2021)
- [Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning](https://mlsanity.com/paper/1510.03519/) (2015)
- [Impact of Training Dataset Size on Neural Answer Selection Models](https://mlsanity.com/paper/1901.10496/) (2019)

## Built on by (most cited first, 24 of 24)

- [NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples](https://mlsanity.com/paper/2410.14669/) (2024)
- [Meta CLIP 2: A Worldwide Scaling Recipe](https://mlsanity.com/paper/2507.22062/) (2025)
- [Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models](https://mlsanity.com/paper/2404.07983/) (2024)
- [jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images](https://mlsanity.com/paper/2412.08802/) (2024)
- [X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP](https://mlsanity.com/paper/2505.05528/) (2025)
- [Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models](https://mlsanity.com/paper/2410.03176/) (2024)
- [Multilingual Diversity Improves Vision-Language Representations](https://mlsanity.com/paper/2405.16915/) (2024)
- [SCAM: A Real-World Typographic Robustness Evaluation for Multimodal Foundation Models](https://mlsanity.com/paper/2504.04893/) (2025)
- [Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment](https://mlsanity.com/paper/2409.19425/) (2024)
- [FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training](https://mlsanity.com/paper/2411.11927/) (2024)
- [mOSCAR: A Large-scale Multilingual and Multimodal Document-level Corpus](https://mlsanity.com/paper/2406.08707/) (2024)
- [Navigating Text-to-Image Generative Bias across Indic Languages](https://mlsanity.com/paper/2408.00283/) (2024)
- [Towards Zero-Shot Multimodal Machine Translation](https://mlsanity.com/paper/2407.13579/) (2024)
- [Uplifting Lower-Income Data: Strategies for Socioeconomic Perspective Shifts in Large Multi-modal Models](https://mlsanity.com/paper/2407.02623/) (2024)
- [Breaking Language Barriers or Reinforcing Bias? A Study of Gender and Racial Disparities in Multilingual Contrastive Vision Language Models](https://mlsanity.com/paper/2505.14160/) (2025)
- [Synthetic Document Question Answering in Hungarian](https://mlsanity.com/paper/2505.23008/) (2025)
- [Multilingual Vision-Language Models, A Survey](https://mlsanity.com/paper/2509.22123/) (2025)
- [Mitigating Cross-modal Representation Bias for Multicultural Image-to-Recipe Retrieval](https://mlsanity.com/paper/2510.20393/) (2025)
- [uCLIP: Parameter-Efficient Multilingual Extension of Vision-Language Models with Unpaired Data](https://mlsanity.com/paper/2511.13036/) (2025)
- [Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance](https://mlsanity.com/paper/2602.01346/) (2026)
- [M-MiniGPT4: Multilingual VLLM Alignment via Translated Data](https://mlsanity.com/paper/2603.29467/) (2026)
- [What Matters for Grocery Product Retrieval with Open Source Vision Language Models](https://mlsanity.com/paper/2605.18029/) (2026)
- [Scaling Vision-Language Models Is Not Enough to Mitigate Bias](https://mlsanity.com/paper/2607.28211/) (2026)
- [Where Do Multilingual Vision-Language Encoders Fail on Low-Resource Languages?](https://mlsanity.com/paper/2608.30725/) (2026)

## Abstract (arXiv)

Today, the exponential rise of large models developed by academic and industrial institutions with the help of massive computing resources raises the question of whether someone without access to such resources can make a valuable scientific contribution. To explore this, we tried to solve the challenging task of multilingual image retrieval having a limited budget of 1,000. As a result, we present NLLB-CLIP - CLIP model with a text encoder from the NLLB model. To train the model, we used an automatically created dataset of 106,246 good-quality images with captions in 201 languages derived from the LAION COCO dataset. We trained multiple models using image and text encoders of various sizes and kept different parts of the model frozen during the training. We thoroughly analyzed the trained models using existing evaluation datasets and newly created XTD200 and Flickr30k-200 datasets. We show that NLLB-CLIP is comparable in quality to state-of-the-art models and significantly outperforms them on low-resource languages.