# Hypernymization of named entity-rich captions for grounding-based multi-modal pretraining

arXiv: https://arxiv.org/abs/2304.13130 · HTML: https://mlsanity.com/paper/2304.13130/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 25 Apr 2023.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Open-Vocabulary Object Detection Using Captions](https://mlsanity.com/paper/2011.10678/) (2020)
- [Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model](https://mlsanity.com/paper/2203.14940/) (2022)
- [Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers](https://mlsanity.com/paper/2004.00849/) (2020)
- [WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning](https://mlsanity.com/paper/2103.01913/) (2021)
- [Revisiting Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/1901.09005/) (2019)
- [How Well Do Self-Supervised Models Transfer?](https://mlsanity.com/paper/2011.13377/) (2020)
- [Zero-Shot Object Detection](https://mlsanity.com/paper/1804.04340/) (2018)
- [Aligning Pretraining for Detection via Object-Level Contrastive Learning](https://mlsanity.com/paper/2106.02637/) (2021)
- [Open Vocabulary Object Detection with Pseudo Bounding-Box Labels](https://mlsanity.com/paper/2111.09452/) (2021)
- [Good News, Everyone! Context driven entity-aware captioning for news images](https://mlsanity.com/paper/1904.01475/) (2019)
- [Spatially Consistent Representation Learning](https://mlsanity.com/paper/2103.06122/) (2021)
- [Transform and Tell: Entity-Aware News Image Captioning](https://mlsanity.com/paper/2004.08070/) (2020)
- [ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues](https://mlsanity.com/paper/2201.06696/) (2022)
- [DAP: Detection-Aware Pre-training with Weak Supervision](https://mlsanity.com/paper/2103.16651/) (2021)

## Abstract (arXiv)

Named entities are ubiquitous in text that naturally accompanies images, especially in domains such as news or Wikipedia articles. In previous work, named entities have been identified as a likely reason for low performance of image-text retrieval models pretrained on Wikipedia and evaluated on named entities-free benchmark datasets. Because they are rarely mentioned, named entities could be challenging to model. They also represent missed learning opportunities for self-supervised models: the link between named entity and object in the image may be missed by the model, but it would not be if the object were mentioned using a more common term. In this work, we investigate hypernymization as a way to deal with named entities for pretraining grounding-based multi-modal models and for fine-tuning on open-vocabulary detection. We propose two ways to perform hypernymization: (1) a ``manual'' pipeline relying on a comprehensive ontology of concepts, and (2) a ``learned'' approach where we train a language model to learn to perform hypernymization. We run experiments on data from Wikipedia and from The New York Times. We report improved pretraining performance on objects of interest following hypernymization, and we show the promise of hypernymization on open-vocabulary detection, specifically on classes not seen during training.