Search Results for author:
Found 2 papers, 0 papers with code
Learning to Compose Diversified Prompts for Image Emotion Classification
We first introduce a prompt tuning method that mimics the pretraining objective of CLIP and thus can leverage the rich image and text semantics entailed in CLIP.
Incremental Learning Using Conditional Adversarial Networks
The discriminator combines real-examples from new data and pseudo-examples generated from the old data distribution to learn representation for both old and new classes.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
