ExpansionNet v2: Block Static Expansion in fast end to end training for Image Captioning. (arXiv:2208.06551v1 [cs.CV])

Expansion methods explore the possibility of performance bottlenecks in the
input length in Deep Learning methods. In this work, we introduce the Block
Static Expansion which distributes and processes the input over a heterogeneous
and arbitrarily big collection of sequences characterized by a different length
compared to the input one. From this method we introduce a new model called
ExpansionNet v2, which is trained using our new training strategy, designed to
be not only effective but also 6 times faster …

arxiv captioning cv image training