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

Transformers are increasingly dominating multi-modal reasoning tasks, such asvisual question answering, achieving state-of-the-art results thanks to theirability to contextualize information using the self-attention and co-attentionmechanisms. These attention modules also play a role in other computer visiontasks including object detection and image segmentation. Unlike Transformersthat only use self-attention, Transformers with co-attention require toconsider multiple attention maps in parallel in order to highlight theinformation that is relevant to the prediction in the model's input. In thiswork, we propose the first method to explain prediction by anyTransformer-based architecture, including bi-modal Transformers andTransformers with co-attentions. We provide generic solutions and apply theseto the three most commonly used of these architectures: (i) pureself-attention, (ii) self-attention combined with co-attention, and (iii)encoder-decoder attention. We show that our method is superior to all existingmethods which are adapted from single modality explainability.

Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers