Category Feature Transformer for Semantic Segmentation. (arXiv:2308.05581v1 [cs.CV])

Aggregation of multi-stage features has been revealed to play a significant
role in semantic segmentation. Unlike previous methods employing point-wise
summation or concatenation for feature aggregation, this study proposes the
Category Feature Transformer (CFT) that explores the flow of category embedding
and transformation among multi-stage features through the prevalent multi-head
attention mechanism. CFT learns unified feature embeddings for individual
semantic categories from high-level features during each aggregation process
and dynamically broadcasts them to high-resolution features. Integrating the
proposed CFT into …

aggregation arxiv attention embedding feature features flow head multi-head multi-head attention role segmentation semantic stage study through transformation transformer