Supplementary Material I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification

Neural Information Processing Systems 

Our novel I2DFormer which only utilizes the I2DAttention module, outperforms all these baselines in row d). Our model is designed with the problem constraints of our ZSL setting and the resulting information asymmetry in mind.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found