Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval. (arXiv:2204.13913v1 [cs.CV])

Current text-image approaches (e.g., CLIP) typically adopt dual-encoder
architecture us- ing pre-trained vision-language representation. However, these
models still pose non-trivial memory requirements and substantial incre- mental
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 result- ing
model is smaller (39% of the original), faster (1.6x/2.9x for processing
image/text re- spectively), yet performs on par with or bet- ter than …

arxiv compression cv image retrieval stage text text-image