Distilled Dual-Encoder Model for Vision-Language Understanding
Wang, Zekun, Wang, Wenhui, Zhu, Haichao, Liu, Ming, Qin, Bing, Wei, Furu
–arXiv.org Artificial Intelligence
We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster inference speed than fusion-encoder models and enable the pre-computation of images and text during inference. However, the shallow interaction module used in dual-encoder models is insufficient to handle complex vision-language understanding tasks. In order to learn deep interactions of images and text, we introduce cross-modal attention distillation, which uses the image-to-text and text-to-image attention distributions of a fusion-encoder model to guide the training of our dual-encoder model. In addition, we show that applying the cross-modal attention distillation for both pre-training and fine-tuning stages achieves further improvements. Experimental results demonstrate that the distilled dual-encoder model achieves competitive performance for visual reasoning, visual entailment and visual question answering tasks while enjoying a much faster inference speed than fusion-encoder models. Our code and models will be publicly available at https://github.com/kugwzk/Distilled-DualEncoder.
arXiv.org Artificial Intelligence
Oct-17-2022
- Country:
- South America > Chile
- Oceania > Australia
- North America
- United States
- Washington > King County
- Renton (0.04)
- Utah > Salt Lake County
- Salt Lake City (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Massachusetts > Suffolk County
- Boston (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- California
- San Diego County > San Diego (0.04)
- Los Angeles County > Long Beach (0.04)
- Washington > King County
- Canada
- Quebec > Montreal (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- United States
- Europe
- Asia > China
- Heilongjiang Province > Harbin (0.04)
- Hong Kong (0.04)
- Guangdong Province > Shenzhen (0.04)
- Beijing > Beijing (0.04)
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- Genre:
- Research Report > New Finding (0.34)
- Industry:
- Education (0.47)
- Technology: