Hierarchical Dense Correlation Distillation for Few-Shot Segmentation
This work addresses few-shot segmentation for computer vision, offering incremental improvements in segmentation granularity and overfitting reduction.
The paper tackles the problem of few-shot semantic segmentation by proposing a Hierarchically Decoupled Matching Network (HDMNet) that uses transformer self-attention for hierarchical dense features and correlation distillation to reduce overfitting, achieving 50.0% mIoU on COCO in one-shot and 56.0% in five-shot settings.
Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. Previous methods limited to the semantic feature and prototype representation suffer from coarse segmentation granularity and train-set overfitting. In this work, we design Hierarchically Decoupled Matching Network (HDMNet) mining pixel-level support correlation based on the transformer architecture. The self-attention modules are used to assist in establishing hierarchical dense features, as a means to accomplish the cascade matching between query and support features. Moreover, we propose a matching module to reduce train-set overfitting and introduce correlation distillation leveraging semantic correspondence from coarse resolution to boost fine-grained segmentation. Our method performs decently in experiments. We achieve $50.0\%$ mIoU on \coco~dataset one-shot setting and $56.0\%$ on five-shot segmentation, respectively.