Guofan Fan

contrastive learning (1) semantic segmentation (1) feature learning (1) image generation (1) scene understanding (1) self-supervised learning (1) multimodal learning (1) 3d vision (1) multi-modal learning (1) object relationships (1) zero-shot generalization (1) ensemble distillation (1) modular autoencoder (1) controllable generation (1) pattern completion (1) encoder-decoder architecture (1) 3d representation learning (1) generative pretraining (1) cross-modal contrast (1) functional specialization (1)