arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.05451cs.CVcs.CLcs.LG
收藏

ACORT:一种用于参数有效图像描述的紧凑对象关系Transformer

ACORT: A Compact Object Relation Transformer for Parameter Efficient Image Captioning

Universiti Malaya(马来亚大学)

Jia Huei Tan, Ying Hua Tan, Chee Seng Chan, Joon Huang Chuah

摘要:

最近的研究将基于Transformer的架构应用于图像描述,实现了最先进的图像描述性能,充分利用了Transformers在自然语言任务上的成功。不幸的是,虽然这些模型工作得很好,但一个主要缺陷是它们的模型尺寸太大。为此,我们提出了三种图像描述Transformers的参数减少方法:基数编码,跨层参数共享和注意力参数共享。通过结合这些方法,我们提出的ACORT模型的参数比基线模型少3.7倍至21.6倍,而不会影响测试性能。MS-COCO数据集上的结果表明,我们的ACORT模型与基线和SOTA方法相比具有竞争力,CIDER得分>=126。最后,我们提出了定性结果和消融研究,以进一步证明拟议的变化的有效性。代码和预训练模型可在https://github.com/jiahuei/sparse-image-captioning上公开获取。

英文摘要:

Recent research that applies Transformer-based architectures to image captioning has resulted in state-of-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 >=126. 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑