Timezone: »

Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching
Byoungjip Kim · Sungik Choi · Dasol Hwang · Moontae Lee · Honglak Lee

Thu Dec 01 09:00 AM -- 11:00 AM (PST) @ Hall J #142

Despite surprising performance on zero-shot transfer, pre-training a large-scale multimodal model is often prohibitive as it requires a huge amount of data and computing resources. In this paper, we propose a method (BeamCLIP) that can effectively transfer the representations of a large pre-trained multimodal model (CLIP-ViT) into a small target model (e.g., ResNet-18). For unsupervised transfer, we introduce cross-modal similarity matching (CSM) that enables a student model to learn the representations of a teacher model by matching the relative similarity distribution across text prompt embeddings. To better encode the text prompts, we design context-based prompt augmentation (CPA) that can alleviate the lexical ambiguity of input text prompts. Our experiments show that unsupervised representation transfer of a pre-trained vision-language model enables a small ResNet-18 to achieve a better ImageNet-1K top-1 linear probe accuracy (66.2%) than vision-only self-supervised learning (SSL) methods (e.g., SimCLR: 51.8%, SwAV: 63.7%), while closing the gap with supervised learning (69.8%).

Author Information

Byoungjip Kim (LG AI Research)
Sungik Choi (LG AI Research)
Dasol Hwang (LG AI Research)
Moontae Lee (University of Illinois at Chicago)
Honglak Lee (LG AI Research / U. Michigan)

More from the Same Authors