Cai, Wenjie, Xiong, Zheng, Sun, Xianfang ORCID: https://orcid.org/0000-0002-6114-0766, Rosin, Paul L. ORCID: https://orcid.org/0000-0002-4965-3884, Jin, Longcun and Peng, Xinyi 2020. Panoptic segmentation-based attention for image captioning. Applied Sciences 10 (1) , 391. 10.3390/app10010391 |
PDF
- Published Version
Available under License Creative Commons Attribution. Download (4MB) |
Abstract
Image captioning is the task of generating textual descriptions of images. In order to obtain a better image representation, attention mechanisms have been widely adopted in image captioning. However, in existing models with detection-based attention, the rectangular attention regions are not fine-grained, as they contain irrelevant regions (e.g., background or overlapped regions) around the object, making the model generate inaccurate captions. To address this issue, we propose panoptic segmentation-based attention that performs attention at a mask-level (i.e., the shape of the main part of an instance). Our approach extracts feature vectors from the corresponding segmentation regions, which is more fine-grained than current attention mechanisms. Moreover, in order to process features of different classes independently, we propose a dual-attention module which is generic and can be applied to other frameworks. Experimental results showed that our model could recognize the overlapped objects and understand the scene better. Our approach achieved competitive performance against state-of-the-art methods. We made our code available.
Item Type: | Article |
---|---|
Date Type: | Publication |
Status: | Published |
Schools: | Computer Science & Informatics |
Publisher: | MDPI |
ISSN: | 2076-3417 |
Date of First Compliant Deposit: | 2 April 2020 |
Date of Acceptance: | 1 January 2020 |
Last Modified: | 05 May 2023 19:53 |
URI: | https://orca.cardiff.ac.uk/id/eprint/130681 |
Citation Data
Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data
Actions (repository staff only)
Edit Item |