Saved in:
Bibliographic Details
Main Authors: Hu, Jia Cheng, Cavicchioli, Roberto, Capotondi, Alessandro
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2208.06551
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913207847747584
author Hu, Jia Cheng
Cavicchioli, Roberto
Capotondi, Alessandro
author_facet Hu, Jia Cheng
Cavicchioli, Roberto
Capotondi, Alessandro
contents We introduce a method called the Expansion mechanism that processes the input unconstrained by the number of elements in the sequence. By doing so, the model can learn more effectively compared to traditional attention-based approaches. To support this claim, we design a novel architecture ExpansionNet v2 that achieved strong results on the MS COCO 2014 Image Captioning challenge and the State of the Art in its respective category, with a score of 143.7 CIDErD in the offline test split, 140.8 CIDErD in the online evaluation server and 72.9 AllCIDEr on the nocaps validation set. Additionally, we introduce an End to End training algorithm up to 2.8 times faster than established alternatives. Source code available at: https://github.com/jchenghu/ExpansionNet_v2
format Preprint
id arxiv_https___arxiv_org_abs_2208_06551
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning
Hu, Jia Cheng
Cavicchioli, Roberto
Capotondi, Alessandro
Computer Vision and Pattern Recognition
We introduce a method called the Expansion mechanism that processes the input unconstrained by the number of elements in the sequence. By doing so, the model can learn more effectively compared to traditional attention-based approaches. To support this claim, we design a novel architecture ExpansionNet v2 that achieved strong results on the MS COCO 2014 Image Captioning challenge and the State of the Art in its respective category, with a score of 143.7 CIDErD in the offline test split, 140.8 CIDErD in the online evaluation server and 72.9 AllCIDEr on the nocaps validation set. Additionally, we introduce an End to End training algorithm up to 2.8 times faster than established alternatives. Source code available at: https://github.com/jchenghu/ExpansionNet_v2
title Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2208.06551