Abstract
Current text-image approaches (e.g., CLIP) typically adopt dual-encoder architecture using pre-trained vision-language representation. However, these models still pose non-trivial memory requirements and substantial incremental indexing time, which makes them less practical on mobile devices. In this paper, we present an effective two-stage framework to compress large pre-trained dual-encoder for lightweight text-image retrieval. The resulting model is smaller (39% of the original), faster (1.6x/2.9x for processing image/text respectively), yet performs on par with or better than the original full model on Flickr30K and MSCOCO benchmarks. We also open-source an accompanying realistic mobile image search application.- Anthology ID:
- 2022.naacl-main.300
- Volume:
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4085–4090
- Language:
- URL:
- https://aclanthology.org/2022.naacl-main.300
- DOI:
- 10.18653/v1/2022.naacl-main.300
- Cite (ACL):
- Siyu Ren and Kenny Zhu. 2022. Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4085–4090, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval (Ren & Zhu, NAACL 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.naacl-main.300.pdf
- Code
- drsy/motis
- Data
- COCO