摘要:
前面介绍了将VAE+GAN解决零样本学习的方法:f-VAEGAN-D2,这里继续讨论引入生成模型处理零样本学习(Zero-shot Learning, ZSL)问题。论文“Latent Embedding Feedback and Discriminative Features for Zero-S 阅读全文
摘要:
论文链接:Meta-Tuning Loss Functions and Data Augmentation for Few-Shot Object Detection Abstract 现阶段的少样本学习技术可以分为两类:基于微调(fine-tuning)方法和基于元学习(meta-learning 阅读全文