# LG AI Research — [NeurIPS 2022] Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching

- Company: LG AI Research (lgresearch.ai)
- Announced: 2023-02-08
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.lgresearch.ai/blog/view?seq=301
- Record: https://forck.live/items/4909-neurips-2022-transferring-pre-trained-multimodal-representations-with-cross
- Subject: EXAONE

LG AI Research introduced BeamCLIP, a method for transferring representations from large pre-trained multimodal models (e.g., CLIP) to smaller models (e.g., ResNet-18), using Cross-modal Similarity Matching (CSM) and Context-based Prompt Augmentation (CPA), achieving 66.2% linear probe accuracy on ImageNet-1K.

## Evidence

Verbatim from https://www.lgresearch.ai/blog/view?seq=301:

> we introduce BeamCLIP, a method that transfers the representations of a large pre-trained multimodal model such as CLIP, to a small target model such as ResNet-18.

---

Record: https://forck.live/items/4909-neurips-2022-transferring-pre-trained-multimodal-representations-with-cross
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md