<ul><li>Crossmodal knowledge distillation (KD) enhances a unimodal student using a multimodal teacher model.</li><li>A multi-teacher crossmodal KD framework is proposed, integrating CLIP image embeddings with WordNet-relaxed text embeddings.</li><li>This approach reduces label leakage and introduces more diverse textual cues for improved knowledge transfer.</li><li>The method achieves state-of-the-art or second-best results on six public datasets, demonstrating its effectiveness in crossmodal KD.</li></ul>

Crossmodal Knowledge Distillation with WordNet-Relaxed Text Embeddings for Robust Image Classification

Discover more