Visual Attention Prompted Prediction and Learning

arXiv:2310.08420v3 Announce Type: replace
Abstract: Visual explanation (attention)-guided learning uses not only labels but also explanations to guide model reasoning process. While visual attention-guided learning has shown promising results, it requires a large number of explanation annotations that are time-consuming to prepare. However, in many real-world situations, it is usually desired to prompt the model with visual attention without model retraining. For example, when doing AI-assisted cancer classification on a medical image, users (e.g., clinicians) can provide the AI model …

abstract annotations arxiv attention cs.cv guide however labels prediction process prompt reasoning results type visual visual attention while world