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

While large scale pre-training has achieved great achievements in bridgingthe gap between vision and language, it still faces several challenges. First,the cost for pre-training is expensive. Second, there is no efficient way tohandle the data noise which degrades model performance. Third, previous methodsonly leverage limited image-text paired data, while ignoring richersingle-modal data, which may result in poor generalization to single-modaldownstream tasks. In this work, we propose an EfficientCLIP method via EnsembleConfident Learning to obtain a less noisy data subset. Extra rich non-pairedsingle-modal text data is used for boosting the generalization of text branch.We achieve the state-of-the-art performance on Chinese cross-modal retrievaltasks with only 1/10 training resources compared to CLIP and WenLan, whileshowing excellent generalization to single-modal tasks, including textretrieval and text classification.

EfficientCLIP: Efficient Cross-Modal Pre-training by Ensemble Confident Learning and Language Modeling