Hyperparameter Analysis for Image Captioning

06/19/2020

∙

by   Amish Patel, et al.

∙

0

∙

share

In this paper, we perform a thorough sensitivity analysis on state-of-the-art image captioning approaches using two different architectures: CNN+LSTM and CNN+Transformer. Experiments were carried out using the Flickr8k dataset. The biggest takeaway from the experiments is that fine-tuning the CNN encoder outperforms the baseline and all other experiments carried out for both architectures.