ACORT: A compact object relation transformer for parameter efficient image captioning
Recent research that applies Transformer-based architectures to image captioning has resulted in stateof-the-art image captioning performance, capitalising on the success of Transformers on natural language tasks. Unfortunately, though these models work well, one major flaw is their large model size...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
Elsevier
2022
|
| Subjects: | |
| Online Access: | http://eprints.um.edu.my/32731/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Recent research that applies Transformer-based architectures to image captioning has resulted in stateof-the-art image captioning performance, capitalising on the success of Transformers on natural language tasks. Unfortunately, though these models work well, one major flaw is their large model sizes. To this end, we present three parameter reduction methods for image captioning Transformers: Radix Encoding, cross-layer parameter sharing, and attention parameter sharing. By combining these methods, our proposed ACORT models have 3.7x to 21.6x fewer parameters than the baseline model without compromising test performance. Results on the MS-COCO dataset demonstrate that our ACORT models are competitive against baselines and SOTA approaches, with CIDEr score P126. Finally, we present qualitative results and ablation studies to demonstrate the efficacy of the proposed changes further. Code and pre-trained models are publicly available at https://github.com/jiahuei/sparse-image-captioning. (c) 2022 Published by Elsevier B.V. |
|---|