# Learning from Children: Improving Image-Caption Pretraining via Curriculum

arXiv: https://arxiv.org/abs/2305.17540 · HTML: https://mlsanity.com/paper/2305.17540/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 27 May 2023.

## Builds on (most cited first, 16 of 16)

- [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)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [Open-Vocabulary Object Detection Using Captions](https://mlsanity.com/paper/2011.10678/) (2020)
- [Curriculum Learning for Data-Efficient Vision-Language Alignment](https://mlsanity.com/paper/2207.14525/) (2022)
- [ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training](https://mlsanity.com/paper/2209.15270/) (2022)
- [Multi-stage Pre-training over Simplified Multimodal Pre-training Models](https://mlsanity.com/paper/2107.14596/) (2021)

## Built on by (most cited first, 1 of 1)

- [Exploring Curriculum Learning for Vision-Language Tasks: A Study on Small-Scale Multimodal Training](https://mlsanity.com/paper/2410.15509/) (2024)

## Abstract (arXiv)

Image-caption pretraining has been quite successfully used for downstream vision tasks like zero-shot image classification and object detection. However, image-caption pretraining is still a hard problem -- it requires multiple concepts (nouns) from captions to be aligned to several objects in images. To tackle this problem, we go to the roots -- the best learner, children. We take inspiration from cognitive science studies dealing with children's language learning to propose a curriculum learning framework. The learning begins with easy-to-align image caption pairs containing one concept per caption. The difficulty is progressively increased with each new phase by adding one more concept per caption. Correspondingly, the knowledge acquired in each learning phase is utilized in subsequent phases to effectively constrain the learning problem to aligning one new concept-object pair in each phase. We show that this learning strategy improves over vanilla image-caption training in various settings -- pretraining from scratch, using a pretrained image or/and pretrained text encoder, low data regime etc.