PictSure: Pretraining Embeddings Matters for In-Context Learning Image Classifiers 事件

PictSure: Pretraining Embeddings Matters for In-Context Learning Image Classifiers arXiv:2506.14842v2 Announce Type: replace Abstract: Building image classification models remains cumbersome in data-scarce domains, where collecting large labeled datasets is impractical. In-context learning (ICL) is a promising paradigm for few-shot image classification (FSIC), but prior work has underexplored the relative importance of encoder pretraining versus fusion-layer training data. We present PictSure,