APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation
APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation
Few-shot semantic segmentation aims to segment novel-class objects in a given query image with only a few labeled support images. Most advanced solutions exploit a metric learning framework that performs segmentation through matching each query feature to a learned class-specific prototype. However, this framework suffers from biased classification due to …