# Pre-training image-language transformers for open-vocabulary tasks

Source: [Pre-training image-language transformers for open-vocabulary tasks](<https://www.sota2.com/research/paper/68fa6d6b1e209131cea39bb2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:34:23.044Z

Authors: AJ Piergiovanni, Weicheng Kuo, Anelia Angelova

Published: 2022-09-09T16:11:11.000Z

## Abstract

We present a pre-training approach for vision and language transformer models, which is based on a mixture of diverse tasks. We explore both the use of image-text captioning data in pre-training, which does not need additional supervision, as well as object-aware strategies to pre-train the model. We evaluate the method on a number of textgenerative vision+language tasks, such as Visual Question Answering, visual entailment and captioning, and demonstrate large gains over standard pre-training methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2209.04372>)

[PDF](<https://arxiv.org/pdf/2209.04372.pdf>)