ALADIN-All Layer Adaptive Instance Normalization for Fine-grained Style Similarity ICCV_2021
ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity ICCV_2021
Simpler is Better Few-shot Semantic Segmentation with ClassifierWeight Transformer ICCV_2021
Simpler is Better: Few-shot Semantic Segmentation with ClassifierWeight Transformer
Simpler is Better: Few-shot Semantic Segmentation with ClassifierWeight Transformer 2021_ICCV
论文简要介绍
任务：少样本分割问题
贡献：
提出了一种新的少样本分割模型训练范式，与以往的同时关注特征提取器和分类器不同，本文将二者分开，并对分类器使用元学习训练策略。
提出了一种叫做 Classifier Weight Transformer的自适应分类器，其实就是在qkv的注意力基础上...
89 post articles, 12 pages.