Showing cs.CVShow all
2 papers · 1 filter
cs.CV2024
Adaptive Margin Global Classifier for Exemplar-Free Class-Incremental Learning
Zhongren Yao, Xiaobin Chang
Exemplar-free class-incremental learning (EFCIL) presents a significant challenge as the old class samples are absent for new task learning. Due to the severe imbalance between old…
cs.CV2024
IIDM: Image-to-Image Diffusion Model for Semantic Image Synthesis
Feng Liu, Xiaobin Chang
Semantic image synthesis aims to generate high-quality images given semantic conditions, i.e. segmentation masks and style reference images. Existing methods widely adopt generativ…