HM: Hybrid Masking for Few-Shot Segmentation
About
We study few-shot semantic segmentation that aims to segment a target object from a query image when provided with a few annotated support images of the target class. Several recent methods resort to a feature masking (FM) technique to discard irrelevant feature activations which eventually facilitates the reliable prediction of segmentation mask. A fundamental limitation of FM is the inability to preserve the fine-grained spatial details that affect the accuracy of segmentation mask, especially for small target objects. In this paper, we develop a simple, effective, and efficient approach to enhance feature masking (FM). We dub the enhanced FM as hybrid masking (HM). Specifically, we compensate for the loss of fine-grained spatial details in FM technique by investigating and leveraging a complementary basic input masking method. Experiments have been conducted on three publicly available benchmarks with strong few-shot segmentation (FSS) baselines. We empirically show improved performance against the current state-of-the-art methods by visible margins across different benchmarks. Our code and trained models are available at: https://github.com/moonsh/HM-Hybrid-Masking
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Few-shot Semantic Segmentation | COCO-20^i v1.0 | mIoU (Overall)50.6 | 70 | |
| Few-shot Semantic Segmentation | COCO-20i -> PASCAL-5i cross-dataset | mIoU70.9 | 70 | |
| Few-shot Semantic Segmentation | PASCAL-5i (test) | 5-Shot mIoU70.9 | 65 | |
| Few-shot Segmentation | FSS-1000 1.0 (test) | mIoU90.5 | 20 |