Augmenting Vision Language Pretraining by Learning Codebook with Visual Semantics

31 Jul 2022  ·  Xiaoyuan Guo, Jiali Duan, C. -C. Jay Kuo, Judy Wawira Gichoya, Imon Banerjee ·

Language modality within the vision language pretraining framework is innately discretized, endowing each word in the language vocabulary a semantic meaning. In contrast, visual modality is inherently continuous and high-dimensional, which potentially prohibits the alignment as well as fusion between vision and language modalities. We therefore propose to "discretize" the visual representation by joint learning a codebook that imbues each visual token a semantic. We then utilize these discretized visual semantics as self-supervised ground-truths for building our Masked Image Modeling objective, a counterpart of Masked Language Modeling which proves successful for language models. To optimize the codebook, we extend the formulation of VQ-VAE which gives a theoretic guarantee. Experiments validate the effectiveness of our approach across common vision-language benchmarks.

PDF Abstract


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.