English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Vision and Language Pretraining has become the prevalent approach fortackling multimodal downstream tasks. The current trend is to move towards everlarger models and pretraining datasets. This computational headlong rush doesnot seem reasonable in the long term to move toward sustainable solutions, andde facto excludes academic laboratories with limited resources. In this work,we propose a new framework, dubbed ViCHA, that efficiently exploits the inputdata to boost the learning by: (a) a new hierarchical cross-modal alignmentloss, (b) new self-supervised scheme based on masked image modeling, (c)leveraging image-level annotations, called Visual Concepts, obtained withexisting foundation models such as CLIP to boost the performance of the imageencoder. Although pretrained on four times less data, our ViCHA strategyoutperforms other approaches on several downstream tasks such as Image-TextRetrieval, VQA, Visual Reasoning, Visual Entailment and Visual Grounding. Thecode will be made publicly available here: https://github.com/mshukor/ViCHA

Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment