2 papers
cs.CV2023
IG Captioner: Information Gain Captioners are Strong Zero-shot Classifiers
Chenglin Yang, Siyuan Qiao, Yuan Cao +4
Generative training has been demonstrated to be powerful for building visual-language models. However, on zero-shot discriminative benchmarks, there is still a performance gap betw…
cs.CV2023
De-Diffusion Makes Text a Strong Cross-Modal Interface
Chen Wei, Chenxi Liu, Siyuan Qiao +3
We demonstrate text as a strong cross-modal interface. Rather than relying on deep embeddings to connect image and language as the interface representation, our approach represents…