ViLT Vision-and-Language Transformer Without Convolution or Region Supervision

ViLT:Vision-and-LanguageTransformerWithoutConvolutionorRegionSupervisionWonjaeKim1†BokyungSon1IldooKim2AbstractVisualEmbeddingSchemaVision-and-LanguagePre-training(VLP)hasim-RegionFeatureImageCNNR...