Hierarchical Dense Correlation Distillation for Few-Shot Segmentation
Bohao Peng, Zhuotao Tian, Xiaoyang Wu, Chenyao Wang, Shu Liu, Jingyong Su, Jiaya Jia
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/pbihao/hdmnetOfficialIn paperpytorch★ 112
Abstract
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 ~dataset one-shot setting and 56.0\% on five-shot segmentation, respectively.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| COCO-20i (1-shot) | HDMNet (VGG-16) | Mean IoU | 45.9 | — | Unverified |
| COCO-20i (1-shot) | HDMNet (ResNet-50) | Mean IoU | 50 | — | Unverified |
| COCO-20i (5-shot) | HDMNet (ResNet-50) | Mean IoU | 56 | — | Unverified |
| COCO-20i (5-shot) | HDMNet (VGG-16) | Mean IoU | 52.4 | — | Unverified |
| PASCAL-5i (1-Shot) | HDMNet (VGG-16) | Mean IoU | 65.1 | — | Unverified |
| PASCAL-5i (1-Shot) | HDMNet (ResNet-50) | Mean IoU | 69.4 | — | Unverified |
| PASCAL-5i (5-Shot) | HDMNet (ResNet-50) | Mean IoU | 71.8 | — | Unverified |
| PASCAL-5i (5-Shot) | HDMNet (VGG-16) | Mean IoU | 69.3 | — | Unverified |