E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
Haiyang Xu, Ming Yan, Chenliang Li, Bin Bi, Songfang Huang, Wenming Xiao, Fei Huang
Abstract
Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly adopt a two-step training procedure, which firstly employs a pre-trained object detector to extract region-based visual features, then concatenates the image representation and text embedding as the input of Transformer to train. However, these methods face problems of using task-specific visual representation of the specific object detector for generic cross-modal understanding, and the computation inefficiency of two-stage pipeline. In this paper, we propose the first end-to-end vision-language pre-trained model for both V+L understanding and generation, namely E2E-VLP, where we build a unified Transformer framework to jointly learn visual representation, and semantic alignments between image and text. We incorporate the tasks of object detection and image captioning into pre-training with a unified Transformer encoder-decoder architecture for enhancing visual learning. An extensive set of experiments have been conducted on well-established vision-language downstream tasks to demonstrate the effectiveness of this novel VLP paradigm.- Anthology ID:
- 2021.acl-long.42
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 503–513
- Language:
- URL:
- https://aclanthology.org/2021.acl-long.42
- DOI:
- 10.18653/v1/2021.acl-long.42
- Cite (ACL):
- Haiyang Xu, Ming Yan, Chenliang Li, Bin Bi, Songfang Huang, Wenming Xiao, and Fei Huang. 2021. E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 503–513, Online. Association for Computational Linguistics.
- Cite (Informal):
- E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning (Xu et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.acl-long.42.pdf
- Data
- COCO, Flickr30k, Visual Genome, Visual Question Answering