%0 Generic %D 2022 %T Transformer Module Networks for Systematic Generalization in Visual Question Answering %A Moyuru Yamada %A Vanessa D'Amario %A Kentaro Takemoto %A Xavier Boix %A Tomotake Sasaki %X Transformer-based models achieve great performance on Visual Question Answering (VQA). How- ever, when we evaluate them on systematic generalization, i.e., handling novel combinations of known concepts, their performance degrades. Neural Module Networks (NMNs) are a promising approach for systematic generalization that consists on composing modules, i.e., neural networks that tackle a sub-task. Inspired by Transformers and NMNs, we propose Transformer Module Network (TMN), a novel Transformer-based model for VQA that dynamically composes modules into a question-specific Transformer network. TMNs achieve state-of-the-art systematic generalization performance in three VQA datasets, namely, CLEVR-CoGenT, CLOSURE and GQA-SGL, in some cases improving more than 30% over standard Transformers. %8 02/2022 %2 https://hdl.handle.net/1721.1/139843