This blogpost will highlight the main ideas, concepts and findings presented in the Bachelor thesis on Visual Question Answering (VQA) with Knowledge-based Semantics that considers training a VQA model with strong semantic and conceptual understanding by learning towards a latent space spanned by the Conceptnet Numberbatch embeddings on the OK-VQA dataset. The blog post will revisit the model formulation, yet keep an emphasis on the proposed idea of presenting VQA models with strong semantic and conceptual understanding rather than solely focusing on accuracy as the performance metric. In the process, explainability tools are exploited.
You May Also Enjoy
less than 1 minute read
This blogpost will examine whether model biases can be mitigated by training a Variational Fair Autoencoder for Heterogeneous Mixed Type Data (VFAE-HM) following the modeling approach of Louizos, C. et al.. Additionally, the approach of Ma, C. et al. is considered for determining proper output distributions for the decoder of the VFAE.