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 © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
- Frequency modulation,
- Semantics,
- Feature masking,
- Few-shot learning,
- Few-shot segmentation,
- Fine grained,
- Masking technique,
- Query images,
- Segmentation masks,
- Semantic segmentation,
- Shot segmentation,
- Target object,
- Computer Vision and Pattern Recognition (cs.CV)
IR Deposit conditions: non-described