Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning
arXiv:2208.06551 · doi:10.1109/BigData59044.2023.10386812
Abstract
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
References in corpus (5)
- MLP-Mixer: An all-MLP Architecture for Vision
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
- GIT: A Generative Image-to-text Transformer for Vision and Language
- Exploring the sequence length bottleneck in the Transformer for Image Captioning
- A request for clarity over the End of Sequence token in the Self-Critical Sequence Training