论文标题
更苗条，更快：轻质文本图像检索的两阶段模型压缩
Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval
论文作者
论文摘要
当前的文本图像方法（例如，剪辑）通常使用预训练的视觉语言表示来采用双编码器架构。但是，这些模型仍然构成了非平凡的内存需求和大量的增量索引时间，这使得它们在移动设备上的实用性降低了。在本文中，我们提出了一个有效的两阶段框架，以压缩大型预训练的双重编码器，以进行轻质的文本图像检索。所得的模型较小（原始模型的39％），更快（分别用于处理图像/文本的1.6倍/2.9倍），但与Flickr30k和Mscoco基准上的原始完整模型相当或更好。我们还开源一个随附的现实移动图像搜索应用程序。
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.
