Few-shot image generation (FSIG) aims to learn to generate new and diver...
Large vision-language models (VLMs) such as GPT-4 have achieved unpreced...
Recently, diffusion models (DMs) have demonstrated their advantageous
po...
Conventional Few-shot classification (FSC) aims to recognize samples fro...
This work investigates the compatibility between label smoothing (LS) an...
Modern GANs excel at generating high quality and diverse images. However...
Cross-domain few-shot classification task (CD-FSC) combines few-shot
cla...