Abstract
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 compared to the standard approach of recent works in Image Captioning. Our new model achieves the state of art performance over the MS-COCO 2014 captioning challenge with a score of 143.7 CIDEr-D in the offline test split, 140.8 CIDEr-D in the online evaluation server and 72.9 All-CIDEr on the nocaps validation set. Source code available at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2208.06551
